Martin Jaggi

291 papers A* 68A 15B 1Misc 2Journal 178Unranked 26
YearRankTypeTitle / Venue / Authors
2026 J jnl
Leveraging the True Depth of LLMs.
Trans. Mach. Learn. Res.
Ramón Calvo González, Daniele Paliotta, Matteo Pagliardini, Martin Jaggi, François Fleuret
2026 J jnl
Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs.
Trans. Mach. Learn. Res.
Thierry Bossy, Julien Tuan Tu Vignoud, Tahseen Rabbani, Juan Ramón Troncoso-Pastoriza, Martin Jaggi
2025 J jnl
A Split-Client Approach to Second-Order Optimization.
CoRR
El Mahdi Chayti, Martin Jaggi
2025 A* conf
Attention with Markov: A Curious Case of Single-layer Transformers.
ICLR
Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar
2025 J jnl
Benchmarking Optimizers for Large Language Model Pretraining.
CoRR
Andrei Semenov, Matteo Pagliardini, Martin Jaggi
2025 J jnl
Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining.
CoRR
Dongyang Fan, Diba Hashemi, Sai Praneeth Karimireddy, Martin Jaggi
2025 J jnl
Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs.
CoRR
Dongyang Fan, Vinko Sabolcec, Matin Ansaripour, Ayush Kumar Tarun, Martin Jaggi, Antoine Bosselut, Imanol Schlag
2025 A* conf
CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference.
ICLR
Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi
2025 J jnl
DISCO: A Browser-Based Privacy-Preserving Framework for Distributed Collaborative Learning.
CoRR
Julien Tuan Tu Vignoud, Valérian Rousset, Hugo El Guedj, Ignacio Aleman, Walid Bennaceur, Batuhan Faik Derinbay, Eduard Durech, Damien Gengler, Lucas Giordano, Felix Grimberg, Franziska Lippoldt, Christina Kopidaki, Jiafan Liu, Lauris Lopata, Nathan Maire, Paul Mansat, Martin Milenkoski, Emmanuel Omont, Günes Özgün, Mina Petrovic, Francesco Posa, Morgan Ridel, Giorgio Savini, Marcel Torne, Lucas Trognon, Alyssa Unell, Olena Zavertiaieva, Sai Praneeth Karimireddy, Tahseen Rabbani, Mary-Anne Hartley, Martin Jaggi
2025 A* conf
Effective Interplay between Sparsity and Quantization: From Theory to Practice.
ICLR
Simla Burcu Harma, Ayan Chakraborty, Elizaveta Kostenok, Danila Mishin, Dongho Ha, Babak Falsafi, Martin Jaggi, Ming Liu, Yunho Oh, Suvinay Subramanian, Amir Yazdanbakhsh
2025 J jnl
Enhancing Multilingual LLM Pretraining with Model-Based Data Selection.
CoRR
Bettina Messmer, Vinko Sabolcec, Martin Jaggi
2025 J jnl
FineWeb2: One Pipeline to Scale Them All - Adapting Pre-Training Data Processing to Every Language.
CoRR
Guilherme Penedo, Hynek Kydlícek, Vinko Sabolcec, Bettina Messmer, Negar Foroutan, Amir Hossein Kargaran, Colin Raffel, Martin Jaggi, Leandro von Werra, Thomas Wolf
2025 J jnl
GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining.
CoRR
Simin Fan, Maria Ios Glarou, Martin Jaggi
2025 J jnl
Gradient-Normalized Smoothness for Optimization with Approximate Hessians.
CoRR
Andrei Semenov, Martin Jaggi, Nikita Doikov
2025 A conf
Improving Stochastic Cubic Newton with Momentum.
AISTATS
El Mahdi Chayti, Nikita Doikov, Martin Jaggi
2025 A* conf
Intrinsic User-Centric Interpretability through Global Mixture of Experts.
ICLR
Vinitra Swamy, Syrielle Montariol, Julian Blackwell, Jibril Frej, Martin Jaggi, Tanja Käser
2025 J jnl
Leveraging the true depth of LLMs.
CoRR
Ramón Calvo González, Daniele Paliotta, Matteo Pagliardini, Martin Jaggi, François Fleuret
2025 J jnl
Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs.
CoRR
Thierry Bossy, Julien Tuan Tu Vignoud, Tahseen Rabbani, Juan Ramón Troncoso-Pastoriza, Martin Jaggi
2025 J jnl
NeuralGrok: Accelerate Grokking by Neural Gradient Transformation.
CoRR
Xinyu Zhou, Simin Fan, Martin Jaggi, Jie Fu
2025 A* conf
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists.
ICML
Dongyang Fan, Bettina Messmer, Nikita Doikov, Martin Jaggi
2025 J jnl
Semantic uncertainty in advanced decoding methods for LLM generation.
CoRR
Darius Foodeei, Simin Fan, Martin Jaggi
2025 J jnl
Stochastic Difference-of-Convex Optimization with Momentum.
CoRR
El Mahdi Chayti, Martin Jaggi
2025 J jnl
Stochastic Optimization with Random Search.
CoRR
El Mahdi Chayti, Taha el Bakkali el Kadi, Omar Saadi, Martin Jaggi
2025 J jnl
TiMoE: Time-Aware Mixture of Language Experts.
CoRR
Robin Faro, Dongyang Fan, Tamar Alphaidze, Martin Jaggi
2025 J jnl
Towards Fully FP8 GEMM LLM Training at Scale.
CoRR
Alejandro Hernández-Cano, Dhia Garbaya, Imanol Schlag, Martin Jaggi
2025 J jnl
Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler.
CoRR
Aleksandr Dremov, Alexander Hägele, Atli Kosson, Martin Jaggi
2025 J jnl
Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler.
Trans. Mach. Learn. Res.
Aleksandr Dremov, Alexander Hägele, Atli Kosson, Martin Jaggi
2025 J jnl
URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training.
CoRR
Dongyang Fan, Vinko Sabolcec, Martin Jaggi
2025 J jnl
Using Machine Learning for move sequence visualization and generation in climbing.
CoRR
Thomas Rimbot, Martin Jaggi, Luis Barba
2025 J jnl
Weight Decay may matter more than muP for Learning Rate Transfer in Practice.
CoRR
Atli Kosson, Jeremy Welborn, Yang Liu, Martin Jaggi, Xi Chen
2025 J jnl
α-LoRA: Effective Fine-Tuning via Base Model Rescaling.
CoRR
Aymane El Firdoussi, El Mahdi Chayti, Mohamed El Amine Seddik, Martin Jaggi
2024 J jnl
A New First-Order Meta-Learning Algorithm with Convergence Guarantees.
CoRR
El Mahdi Chayti, Martin Jaggi
2024 A* conf
Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training.
NeurIPS
Atli Kosson, Bettina Messmer, Martin Jaggi
2024 J jnl
Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training.
CoRR
Atli Kosson, Bettina Messmer, Martin Jaggi
2024 J jnl
Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains.
CoRR
Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar
2024 A* conf
CoBo: Collaborative Learning via Bilevel Optimization.
NeurIPS
Diba Hashemi, Lie He, Martin Jaggi
2024 J jnl
CoBo: Collaborative Learning via Bilevel Optimization.
CoRR
Diba Hashemi, Lie He, Martin Jaggi
2024 J jnl
Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants.
CoRR
Beatriz Borges, Negar Foroutan, Deniz Bayazit, Anna Sotnikova, Syrielle Montariol, Tanya Nazaretzky, Mohammadreza Banaei, Alireza Sakhaeirad, Philippe Servant, Seyed Parsa Neshaei, Jibril Frej, Angelika Romanou, Gail Weiss, Sepideh Mamooler, Zeming Chen, Simin Fan, Silin Gao, Mete Ismayilzada, Debjit Paul, Alexandre Schöpfer, Andrej Janchevski, Anja Tiede, Clarence Linden, Emanuele Troiani, Francesco Salvi, Freya Behrens, Giacomo Orsi, Giovanni Piccioli, Hadrien Sevel, Louis Coulon, Manuela Pineros-Rodriguez, Marin Bonnassies, Pierre Hellich, Puck van Gerwen, Sankalp Gambhir, Solal Pirelli, Thomas Blanchard, Timothée Callens, Toni Abi Aoun, Yannick Calvino Alonso, Yuri Cho, Alberto Silvio Chiappa, Antonio Sclocchi, Étienne Bruno, Florian Hofhammer, Gabriel Pescia, Geovani Rizk, Leello Dadi, Lucas Stoffl, Manoel Horta Ribeiro, Matthieu Bovel, Yueyang Pan, Aleksandra Radenovic, Alexandre Alahi, Alexander Mathis, Anne-Florence Bitbol, Boi Faltings, Cécile Hébert, Devis Tuia, François Maréchal, George Candea, Giuseppe Carleo, Jean-Cédric Chappelier, Nicolas Flammarion, Jean-Marie Fürbringer, Jean-Philippe Pellet, Karl Aberer, Lenka Zdeborová, Marcel Salathé, Martin Jaggi, Martin Rajman, Mathias Payer, Matthieu Wyart, Michael Gastpar, Michele Ceriotti, Ola Svensson, Olivier Lévêque, Paolo Ienne, Rachid Guerraoui, Robert West, Sanidhya Kashyap, Valerio Piazza, Viesturs Simanis, Viktor Kuncak, Volkan Cevher, Philippe Schwaller, Sacha Friedli, Patrick Jermann, Tanja Käser, Antoine Bosselut
2024 A* conf
DOGE: Domain Reweighting with Generalization Estimation.
ICML
Simin Fan, Matteo Pagliardini, Martin Jaggi
2024 J jnl
Deep Grokking: Would Deep Neural Networks Generalize Better?
CoRR
Simin Fan, Razvan Pascanu, Martin Jaggi
2024 A* conf
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging.
NeurIPS
Matteo Pagliardini, Amirkeivan Mohtashami, François Fleuret, Martin Jaggi
2024 J jnl
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging.
CoRR
Matteo Pagliardini, Amirkeivan Mohtashami, François Fleuret, Martin Jaggi
2024 J jnl
Effective Interplay between Sparsity and Quantization: From Theory to Practice.
CoRR
Simla Burcu Harma, Ayan Chakraborty, Elizaveta Kostenok, Danila Mishin, Dongho Ha, Babak Falsafi, Martin Jaggi, Ming Liu, Yunho Oh, Suvinay Subramanian, Amir Yazdanbakhsh
2024 A* conf
Ghost Noise for Regularizing Deep Neural Networks.
AAAI
Atli Kosson, Dongyang Fan, Martin Jaggi
2024 J jnl
HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation.
CoRR
Xinyu Zhou, Simin Fan, Martin Jaggi
2024 J jnl
Improving Stochastic Cubic Newton with Momentum.
CoRR
El Mahdi Chayti, Nikita Doikov, Martin Jaggi
2024 J jnl
InterpretCC: Conditional Computation for Inherently Interpretable Neural Networks.
CoRR
Vinitra Swamy, Julian Blackwell, Jibril Frej, Martin Jaggi, Tanja Käser
2024 A* conf
LASER: Linear Compression in Wireless Distributed Optimization.
ICML
Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael Gastpar
2024 A* conf
Layer-wise linear mode connectivity.
ICLR
Linara Adilova, Maksym Andriushchenko, Michael Kamp, Asja Fischer, Martin Jaggi
2024 J jnl
MyThisYourThat for interpretable identification of systematic bias in federated learning for biomedical images.
npj Digit. Medicine
Klavdiia Naumova, Arnout Devos, Sai Praneeth Karimireddy, Martin Jaggi, Mary-Anne Hartley
2024 A* conf
On Convergence of Incremental Gradient for Non-convex Smooth Functions.
ICML
Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich, Martin Jaggi
2024 J jnl
On-device Collaborative Language Modeling via a Mixture of Generalists and Specialists.
CoRR
Dongyang Fan, Bettina Messmer, Martin Jaggi
2024 J jnl
Personalized Collaborative Fine-Tuning for On-Device Large Language Models.
CoRR
Nicolas Wagner, Dongyang Fan, Martin Jaggi
2024 A* conf
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.
NeurIPS
Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman
2024 J jnl
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.
CoRR
Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman
2024 A* conf
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks.
ICML
Atli Kosson, Bettina Messmer, Martin Jaggi
2024 A* conf
Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations.
NeurIPS
Alexander Hägele, Elie Bakouch, Atli Kosson, Loubna Ben Allal, Leandro von Werra, Martin Jaggi
2024 J jnl
Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations.
CoRR
Alexander Hägele, Elie Bakouch, Atli Kosson, Loubna Ben Allal, Leandro von Werra, Martin Jaggi
2024 A* conf
Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions.
ICML
Nikita Doikov, Sebastian U. Stich, Martin Jaggi
2024 A* conf
The Privacy Power of Correlated Noise in Decentralized Learning.
ICML
Youssef Allouah, Anastasia Koloskova, Aymane El Firdoussi, Martin Jaggi, Rachid Guerraoui
2024 J jnl
The Privacy Power of Correlated Noise in Decentralized Learning.
CoRR
Youssef Allouah, Anastasia Koloskova, Aymane El Firdoussi, Martin Jaggi, Rachid Guerraoui
2024 J jnl
Towards an empirical understanding of MoE design choices.
CoRR
Dongyang Fan, Bettina Messmer, Martin Jaggi
2024 J jnl
Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods.
Trans. Mach. Learn. Res.
El Mahdi Chayti, Martin Jaggi, Nikita Doikov
2023 A* conf
Agree to Disagree: Diversity through Disagreement for Better Transferability.
ICLR
Matteo Pagliardini, Martin Jaggi, François Fleuret, Sai Praneeth Karimireddy
2023 J jnl
Beyond Spectral Gap: The Role of the Topology in Decentralized Learning.
J. Mach. Learn. Res.
Thijs Vogels, Hadrien Hendrikx, Martin Jaggi
2023 J jnl
Beyond spectral gap (extended): The role of the topology in decentralized learning.
CoRR
Thijs Vogels, Hadrien Hendrikx, Martin Jaggi
2023 J jnl
CoTFormer: More Tokens With Attention Make Up For Less Depth.
CoRR
Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi
2023 A* conf
Collaborative Learning via Prediction Consensus.
NeurIPS
Dongyang Fan, Celestine Mendler-Dünner, Martin Jaggi
2023 J jnl
Collaborative Learning via Prediction Consensus.
CoRR
Dongyang Fan, Celestine Mendler-Dünner, Martin Jaggi
2023 J jnl
Controllable Topic-Focused Abstractive Summarization.
CoRR
Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff
2023 J jnl
DeepBreath - automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries.
npj Digit. Medicine
Julien Heitmann, Alban Glangetas, Jonathan Doenz, Juliane Dervaux, Deeksha M. Shama, Daniel Hinjos Garcia, Mohamed Rida Benissa, Aymeric Cantais, Alexandre Perez, Daniel Müller, Tatjana Chavdarova, Isabelle Ruchonnet-Metrailler, Johan N. Siebert, Laurence Lacroix, Martin Jaggi, Alain Gervaix, Mary-Anne Hartley, Florence Hugon, Derrick Fassbind, Makura Barro, Georges Bediang, N. E. L. Hafidi, M. Bouskraoui, Idrissa Ba
2023 J jnl
DoGE: Domain Reweighting with Generalization Estimation.
CoRR
Simin Fan, Matteo Pagliardini, Martin Jaggi
2023 A* conf
Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention.
NeurIPS
Matteo Pagliardini, Daniele Paliotta, Martin Jaggi, François Fleuret
2023 J jnl
Faster Causal Attention Over Large Sequences Through Sparse Flash Attention.
CoRR
Matteo Pagliardini, Daniele Paliotta, Martin Jaggi, François Fleuret
2023 J jnl
Ghost Noise for Regularizing Deep Neural Networks.
CoRR
Atli Kosson, Dongyang Fan, Martin Jaggi
2023 J jnl
Hardware-Efficient Transformer Training via Piecewise Affine Operations.
CoRR
Atli Kosson, Martin Jaggi
2023 J jnl
Irreducible Curriculum for Language Model Pretraining.
CoRR
Simin Fan, Martin Jaggi
2023 J jnl
LASER: Linear Compression in Wireless Distributed Optimization.
CoRR
Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael C. Gastpar
2023 J jnl
Landmark Attention: Random-Access Infinite Context Length for Transformers.
CoRR
Amirkeivan Mohtashami, Martin Jaggi
2023 J jnl
Layerwise Linear Mode Connectivity.
CoRR
Linara Adilova, Asja Fischer, Martin Jaggi
2023 A* conf
Linearization Algorithms for Fully Composite Optimization.
COLT
Maria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion
2023 J jnl
Linearization Algorithms for Fully Composite Optimization.
CoRR
Maria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion
2023 J jnl
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models.
CoRR
Zeming Chen, Alejandro Hernández-Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, Alexandre Sallinen, Alireza Sakhaeirad, Vinitra Swamy, Igor Krawczuk, Deniz Bayazit, Axel Marmet, Syrielle Montariol, Mary-Anne Hartley, Martin Jaggi, Antoine Bosselut
2023 A* conf
MultiMoDN - Multimodal, Multi-Task, Interpretable Modular Networks.
NeurIPS
Vinitra Swamy, Malika Satayeva, Jibril Frej, Thierry Bossy, Thijs Vogels, Martin Jaggi, Tanja Käser, Mary-Anne Hartley
2023 J jnl
MultiModN- Multimodal, Multi-Task, Interpretable Modular Networks.
CoRR
Vinitra Swamy, Malika Satayeva, Jibril Frej, Thierry Bossy, Thijs Vogels, Martin Jaggi, Tanja Käser, Mary-Anne Hartley
2023 A* conf
Multiplication-Free Transformer Training via Piecewise Affine Operations.
NeurIPS
Atli Kosson, Martin Jaggi
2023 J jnl
Provably Personalized and Robust Federated Learning.
CoRR
Mariel A. Werner, Lie He, Sai Praneeth Karimireddy, Michael I. Jordan, Martin Jaggi
2023 J jnl
Provably Personalized and Robust Federated Learning.
Trans. Mach. Learn. Res.
Mariel A. Werner, Lie He, Michael I. Jordan, Martin Jaggi, Sai Praneeth Karimireddy
2023 A* conf
Random-Access Infinite Context Length for Transformers.
NeurIPS
Amirkeivan Mohtashami, Martin Jaggi
2023 J jnl
Rotational Optimizers: Simple & Robust DNN Training.
CoRR
Atli Kosson, Bettina Messmer, Martin Jaggi
2023 — conf
SIMSUM: Document-level Text Simplification via Simultaneous Summarization.
ACL (1)
Sofia Blinova, Xinyu Zhou, Martin Jaggi, Carsten Eickhoff, Seyed Ali Bahrainian
2023 A* conf
Second-Order Optimization with Lazy Hessians.
ICML
Nikita Doikov, El Mahdi Chayti, Martin Jaggi
2023 J jnl
Shuffle SGD is Always Better than SGD: Improved Analysis of SGD with Arbitrary Data Orders.
CoRR
Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich, Martin Jaggi
2023 A* conf
Special Properties of Gradient Descent with Large Learning Rates.
ICML
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
2023 J jnl
Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods.
CoRR
El Mahdi Chayti, Nikita Doikov, Martin Jaggi
2022 J jnl
Accuracy Boosters: Epoch-Driven Mixed-Mantissa Block Floating-Point for DNN Training.
CoRR
Simla Burcu Harma, Canberk Sönmez, Babak Falsafi, Martin Jaggi, Yunho Oh
2022 J jnl
Agree to Disagree: Diversity through Disagreement for Better Transferability.
CoRR
Matteo Pagliardini, Martin Jaggi, François Fleuret, Sai Praneeth Karimireddy
2022 J jnl
Beyond spectral gap: The role of the topology in decentralized learning.
CoRR
Thijs Vogels, Hadrien Hendrikx, Martin Jaggi
2022 A* conf
Beyond spectral gap: the role of the topology in decentralized learning.
NeurIPS
Thijs Vogels, Hadrien Hendrikx, Martin Jaggi
2022 J jnl
Byzantine-Robust Decentralized Learning via Self-Centered Clipping.
CoRR
Lie He, Sai Praneeth Karimireddy, Martin Jaggi
2022 A* conf
Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing.
ICLR
Sai Praneeth Karimireddy, Lie He, Martin Jaggi
2022 J jnl
Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods.
CoRR
Amirkeivan Mohtashami, Sebastian U. Stich, Martin Jaggi
2022 J jnl
Data-heterogeneity-aware Mixing for Decentralized Learning.
CoRR
Yatin Dandi, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich
2022 A* conf
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings.
NeurIPS
Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Telenczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux
2022 J jnl
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings.
CoRR
Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Telenczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux
2022 A* conf
Implicit Gradient Alignment in Distributed and Federated Learning.
AAAI
Yatin Dandi, Luis Barba, Martin Jaggi
2022 J jnl
Improving Generalization via Uncertainty Driven Perturbations.
CoRR
Matteo Pagliardini, Gilberto Manunza, Martin Jaggi, Michael I. Jordan, Tatjana Chavdarova
2022 A conf
Masked Training of Neural Networks with Partial Gradients.
AISTATS
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
2022 J jnl
Modular Clinical Decision Support Networks (MoDN) - Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments.
CoRR
Cécile Trottet, Thijs Vogels, Martin Jaggi, Mary-Anne Hartley
2022 J jnl
On Avoiding Local Minima Using Gradient Descent With Large Learning Rates.
CoRR
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
2022 — conf
SKILL: Structured Knowledge Infusion for Large Language Models.
NAACL-HLT
Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi
2022 J jnl
SKILL: Structured Knowledge Infusion for Large Language Models.
CoRR
Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi
2022 J jnl
Scalable Collaborative Learning via Representation Sharing.
CoRR
Frédéric Berdoz, Abhishek Singh, Martin Jaggi, Ramesh Raskar
2022 J jnl
Second-order optimization with lazy Hessians.
CoRR
Nikita Doikov, El Mahdi Chayti, Martin Jaggi
2022 A* conf
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning.
NeurIPS
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
2022 J jnl
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning.
CoRR
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
2021 J jnl
A Field Guide to Federated Optimization.
CoRR
Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Agüera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas N. Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Hard, Chaoyang He, Samuel Horváth, Zhouyuan Huo, Alex Ingerman, Martin Jaggi, Tara Javidi, Peter Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecný, Sanmi Koyejo, Tian Li, Luyang Liu, Mehryar Mohri, Hang Qi, Sashank J. Reddi, Peter Richtárik, Karan Singhal, Virginia Smith, Mahdi Soltanolkotabi, Weikang Song, Ananda Theertha Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake E. Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, Manzil Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu
2021 A conf
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!
AISTATS
Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtárik, Sebastian U. Stich
2021 J jnl
Advances and Open Problems in Federated Learning.
Found. Trends Mach. Learn.
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
2021 J jnl
An accelerated communication-efficient primal-dual optimization framework for structured machine learning.
Optim. Methods Softw.
Chenxin Ma, Martin Jaggi, Frank E. Curtis, Nathan Srebro, Martin Takác
2021 A* conf
Breaking the centralized barrier for cross-device federated learning.
NeurIPS
Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh
2021 A* conf
Consensus Control for Decentralized Deep Learning.
ICML
Lingjing Kong, Tao Lin, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich
2021 J jnl
Consensus Control for Decentralized Deep Learning.
CoRR
Lingjing Kong, Tao Lin, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich
2021 A conf
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates.
AISTATS
Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi
2021 J jnl
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates.
CoRR
Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi
2021 A* conf
Equinox: Training (for Free) on a Custom Inference Accelerator.
MICRO
Mario Drumond, Louis Coulon, Arash Pourhabibi Zarandi, Ahmet Caner Yüzügüler, Babak Falsafi, Martin Jaggi
2021 A* conf
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning.
ICML
Giovanni Cherubin, Konstantinos Chatzikokolakis, Martin Jaggi
2021 J jnl
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning.
CoRR
Giovanni Cherubin, Konstantinos Chatzikokolakis, Martin Jaggi
2021 Misc conf
Faster Parallel Training of Word Embeddings.
HiPC
Eliza Wszola, Martin Jaggi, Markus Püschel
2021 J jnl
Federated Learning for Malware Detection in IoT Devices.
CoRR
Valerian Rey, Pedro Miguel Sánchez Sánchez, Alberto Huertas Celdrán, Gérôme Bovet, Martin Jaggi
2021 J jnl
IFedAvg: Interpretable Data-Interoperability for Federated Learning.
CoRR
David Roschewitz, Mary-Anne Hartley, Luca Corinzia, Martin Jaggi
2021 J jnl
Implicit Gradient Alignment in Distributed and Federated Learning.
CoRR
Yatin Dandi, Luis Barba, Martin Jaggi
2021 J jnl
Interpreting Language Models Through Knowledge Graph Extraction.
CoRR
Vinitra Swamy, Angelika Romanou, Martin Jaggi
2021 A conf
LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads.
AISTATS
Hossein Shokri Ghadikolaei, Sebastian U. Stich, Martin Jaggi
2021 A* conf
Learning from History for Byzantine Robust Optimization.
ICML
Sai Praneeth Karimireddy, Lie He, Martin Jaggi
2021 — conf
Lightweight Cross-Lingual Sentence Representation Learning.
ACL/IJCNLP (1)
Zhuoyuan Mao, Prakhar Gupta, Chenhui Chu, Martin Jaggi, Sadao Kurohashi
2021 J jnl
Lightweight Cross-Lingual Sentence Representation Learning.
CoRR
Zhuoyuan Mao, Prakhar Gupta, Chenhui Chu, Martin Jaggi, Sadao Kurohashi
2021 J jnl
Linear Speedup in Personalized Collaborative Learning.
CoRR
El Mahdi Chayti, Sai Praneeth Karimireddy, Sebastian U. Stich, Nicolas Flammarion, Martin Jaggi
2021 — conf
Obtaining Better Static Word Embeddings Using Contextual Embedding Models.
ACL/IJCNLP (1)
Prakhar Gupta, Martin Jaggi
2021 J jnl
Obtaining Better Static Word Embeddings Using Contextual Embedding Models.
CoRR
Prakhar Gupta, Martin Jaggi
2021 J jnl
On Second-order Optimization Methods for Federated Learning.
CoRR
Sebastian Bischoff, Stephan Günnemann, Martin Jaggi, Sebastian U. Stich
2021 J jnl
Optimal Model Averaging: Towards Personalized Collaborative Learning.
CoRR
Felix Grimberg, Mary-Anne Hartley, Sai Praneeth Karimireddy, Martin Jaggi
2021 — conf
Prediction of self-reported depression scores using person-generated health data from a virtual 1-year mental health observational study.
DigiBiom@MobiSys
Mariko Makhmutova, Raghu Kainkaryam, Marta Ferreira, Jae Min, Martin Jaggi, Ieuan Clay
2021 J jnl
Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data.
CoRR
Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
2021 A* conf
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data.
ICML
Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
2021 A* conf
RelaySum for Decentralized Deep Learning on Heterogeneous Data.
NeurIPS
Thijs Vogels, Lie He, Anastasia Koloskova, Sai Praneeth Karimireddy, Tao Lin, Sebastian U. Stich, Martin Jaggi
2021 J jnl
RelaySum for Decentralized Deep Learning on Heterogeneous Data.
CoRR
Thijs Vogels, Lie He, Anastasia Koloskova, Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
2021 — conf
Self-Supervised Neural Topic Modeling.
EMNLP (Findings)
Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff
2021 A* conf
Semantic Perturbations with Normalizing Flows for Improved Generalization.
ICCV
Oguz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova
2021 J jnl
Semantic Perturbations with Normalizing Flows for Improved Generalization.
CoRR
Oguz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova
2021 J jnl
Simultaneous Training of Partially Masked Neural Networks.
CoRR
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
2021 A* conf
Taming GANs with Lookahead-Minmax.
ICLR
Tatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich, François Fleuret, Martin Jaggi
2021 J jnl
Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation.
CoRR
Futong Liu, Tao Lin, Martin Jaggi
2021 A* conf
Understanding the effects of data parallelism and sparsity on neural network training.
ICLR
Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr, Martin Jaggi
2021 J jnl
WAFFLE: Weighted Averaging for Personalized Federated Learning.
CoRR
Martin Beaussart, Felix Grimberg, Mary-Anne Hartley, Martin Jaggi
2020 J jnl
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!
CoRR
Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtárik, Sebastian U. Stich
2020 A* conf
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates.
ICML
Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich
2020 J jnl
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates.
CoRR
Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich
2020 J jnl
Byzantine-Robust Learning on Heterogeneous Datasets via Resampling.
CoRR
Lie He, Sai Praneeth Karimireddy, Martin Jaggi
2020 A conf
Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representations.
AISTATS
Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi
2020 J jnl
Data Parallelism in Training Sparse Neural Networks.
CoRR
Namhoon Lee, Philip H. S. Torr, Martin Jaggi
2020 A* conf
Decentralized Deep Learning with Arbitrary Communication Compression.
ICLR
Anastasia Koloskova, Tao Lin, Sebastian U. Stich, Martin Jaggi
2020 A* conf
Don't Use Large Mini-batches, Use Local SGD.
ICLR
Tao Lin, Sebastian U. Stich, Kumar Kshitij Patel, Martin Jaggi
2020 A* conf
Dynamic Model Pruning with Feedback.
ICLR
Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi
2020 J jnl
Dynamic Model Pruning with Feedback.
CoRR
Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi
2020 A* conf
Ensemble Distillation for Robust Model Fusion in Federated Learning.
NeurIPS
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
2020 J jnl
Ensemble Distillation for Robust Model Fusion in Federated Learning.
CoRR
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
2020 A* conf
Evaluating The Search Phase of Neural Architecture Search.
ICLR
Kaicheng Yu, Christian Sciuto, Martin Jaggi, Claudiu Musat, Mathieu Salzmann
2020 A* conf
Extrapolation for Large-batch Training in Deep Learning.
ICML
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
2020 J jnl
Extrapolation for Large-batch Training in Deep Learning.
CoRR
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
2020 J jnl
Learning from History for Byzantine Robust Optimization.
CoRR
Sai Praneeth Karimireddy, Lie He, Martin Jaggi
2020 A conf
Linearly Convergent Frank-Wolfe without Line-Search.
AISTATS
Fabian Pedregosa, Geoffrey Négiar, Armin Askari, Martin Jaggi
2020 — conf
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models.
EMNLP (1)
Mengjie Zhao, Tao Lin, Fei Mi, Martin Jaggi, Hinrich Schütze
2020 J jnl
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models.
CoRR
Mengjie Zhao, Tao Lin, Martin Jaggi, Hinrich Schütze
2020 J jnl
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning.
CoRR
Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh
2020 A* conf
Model Fusion via Optimal Transport.
NeurIPS
Sidak Pal Singh, Martin Jaggi
2020 J jnl
Multi-Head Attention: Collaborate Instead of Concatenate.
CoRR
Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi
2020 A* conf
On the Relationship between Self-Attention and Convolutional Layers.
ICLR
Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi
2020 A* conf
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning.
ICML
Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels, Martin Jaggi, François Fleuret
2020 J jnl
PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning.
CoRR
Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi
2020 A* conf
Practical Low-Rank Communication Compression in Decentralized Deep Learning.
NeurIPS
Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi
2020 J jnl
Secure Byzantine-Robust Machine Learning.
CoRR
Lie He, Sai Praneeth Karimireddy, Martin Jaggi
2020 J jnl
Sparse Communication for Training Deep Networks.
CoRR
Negar Foroutan Eghlidi, Martin Jaggi
2020 J jnl
Taming GANs with Lookahead.
CoRR
Tatjana Chavdarova, Matteo Pagliardini, Martin Jaggi, François Fleuret
2020 — conf
Weight Erosion: An Update Aggregation Scheme for Personalized Collaborative Machine Learning.
DART/DCL@MICCAI
Felix Grimberg, Mary-Anne Hartley, Martin Jaggi, Sai Praneeth Karimireddy
2019 J jnl
Advances and Open Problems in Federated Learning.
CoRR
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
2019 — conf
Better Word Embeddings by Disentangling Contextual n-Gram Information.
NAACL-HLT (1)
Prakhar Gupta, Matteo Pagliardini, Martin Jaggi
2019 J jnl
Better Word Embeddings by Disentangling Contextual n-Gram Information.
CoRR
Prakhar Gupta, Matteo Pagliardini, Martin Jaggi
2019 — conf
Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations.
DGS@ICLR
Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi
2019 — conf
Correlating Twitter Language with Community-Level Health Outcomes.
SMM4H@ACL
Arno Schneuwly, Ralf Grubenmann, Séverine Rion Logean, Mark Cieliebak, Martin Jaggi
2019 J jnl
Correlating Twitter Language with Community-Level Health Outcomes.
CoRR
Arno Schneuwly, Ralf Grubenmann, Séverine Rion Logean, Mark Cieliebak, Martin Jaggi
2019 A conf
Crosslingual Document Embedding as Reduced-Rank Ridge Regression.
WSDM
Martin Josifoski, Ivan S. Paskov, Hristo S. Paskov, Martin Jaggi, Robert West
2019 J jnl
Crosslingual Document Embedding as Reduced-Rank Ridge Regression.
CoRR
Martin Josifoski, Ivan S. Paskov, Hristo S. Paskov, Martin Jaggi, Robert West
2019 J jnl
Decentralized Deep Learning with Arbitrary Communication Compression.
CoRR
Anastasia Koloskova, Tao Lin, Sebastian U. Stich, Martin Jaggi
2019 A* conf
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication.
ICML
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
2019 J jnl
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication.
CoRR
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
2019 A conf
Efficient Greedy Coordinate Descent for Composite Problems.
AISTATS
Sai Praneeth Karimireddy, Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
2019 A* conf
Error Feedback Fixes SignSGD and other Gradient Compression Schemes.
ICML
Sai Praneeth Karimireddy, Quentin Rebjock, Sebastian U. Stich, Martin Jaggi
2019 J jnl
Error Feedback Fixes SignSGD and other Gradient Compression Schemes.
CoRR
Sai Praneeth Karimireddy, Quentin Rebjock, Sebastian U. Stich, Martin Jaggi
2019 J jnl
Evaluating the Search Phase of Neural Architecture Search.
CoRR
Christian Sciuto, Kaicheng Yu, Martin Jaggi, Claudiu Musat, Mathieu Salzmann
2019 J jnl
Forecasting intracranial hypertension using multi-scale waveform metrics.
CoRR
Matthias Hüser, Adrian Kündig, Walter Karlen, Valeria De Luca, Martin Jaggi
2019 J jnl
Model Fusion via Optimal Transport.
CoRR
Sidak Pal Singh, Martin Jaggi
2019 Misc conf
On Linear Learning with Manycore Processors.
HiPC
Eliza Wszola, Celestine Mendler-Dünner, Martin Jaggi, Markus Püschel
2019 J jnl
On Linear Learning with Manycore Processors.
CoRR
Eliza Wszola, Celestine Mendler-Dünner, Martin Jaggi, Markus Püschel
2019 J jnl
On the Relationship between Self-Attention and Convolutional Layers.
CoRR
Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi
2019 J jnl
On the Tunability of Optimizers in Deep Learning.
CoRR
Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels, Martin Jaggi, François Fleuret
2019 A conf
Open-Vocabulary Keyword Spotting with Audio and Text Embeddings.
INTERSPEECH
Niccolò Sacchi, Alexandre Nanchen, Martin Jaggi, Milos Cernak
2019 J jnl
Overcoming Multi-Model Forgetting.
CoRR
Yassine Benyahia, Kaicheng Yu, Kamil Bennani-Smires, Martin Jaggi, Anthony C. Davison, Mathieu Salzmann, Claudiu Musat
2019 A* conf
Overcoming Multi-model Forgetting.
ICML
Yassine Benyahia, Kaicheng Yu, Kamil Bennani-Smires, Martin Jaggi, Anthony C. Davison, Mathieu Salzmann, Claudiu Musat
2019 A* conf
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization.
NeurIPS
Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi
2019 J jnl
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization.
CoRR
Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi
2019 J jnl
Robust Cross-lingual Embeddings from Parallel Sentences.
CoRR
Ali Sabet, Prakhar Gupta, Jean-Baptiste Cordonnier, Robert West, Martin Jaggi
2019 J jnl
Structure Tree-LSTM: Structure-aware Attentional Document Encoders.
CoRR
Khalil Mrini, Claudiu Musat, Michael Baeriswyl, Martin Jaggi
2019 J jnl
SysML: The New Frontier of Machine Learning Systems.
CoRR
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Eric S. Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros G. Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim M. Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konecný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Gordon Murray, Dimitris S. Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Randall Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric P. Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar
2019 A* conf
Unsupervised Scalable Representation Learning for Multivariate Time Series.
NeurIPS
Jean-Yves Franceschi, Aymeric Dieuleveut, Martin Jaggi
2019 J jnl
Unsupervised Scalable Representation Learning for Multivariate Time Series.
CoRR
Jean-Yves Franceschi, Aymeric Dieuleveut, Martin Jaggi
2019 J jnl
Unsupervised robust nonparametric learning of hidden community properties.
Math. Found. Comput.
Mikhail A. Langovoy, Akhilesh Gotmare, Martin Jaggi
2018 A* conf
A Distributed Second-Order Algorithm You Can Trust.
ICML
Celestine Dünner, Aurélien Lucchi, Matilde Gargiani, An Bian, Thomas Hofmann, Martin Jaggi
2018 J jnl
A Distributed Second-Order Algorithm You Can Trust.
CoRR
Celestine Dünner, Aurélien Lucchi, Matilde Gargiani, An Bian, Thomas Hofmann, Martin Jaggi
2018 A conf
Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems.
AISTATS
Sai Praneeth Reddy Karimireddy, Sebastian U. Stich, Martin Jaggi
2018 J jnl
COLA: Communication-Efficient Decentralized Linear Learning.
CoRR
Lie He, An Bian, Martin Jaggi
2018 A* conf
COLA: Decentralized Linear Learning.
NeurIPS
Lie He, An Bian, Martin Jaggi
2018 J jnl
Don't Use Large Mini-Batches, Use Local SGD.
CoRR
Tao Lin, Sebastian U. Stich, Martin Jaggi
2018 J jnl
Efficient Greedy Coordinate Descent for Composite Problems.
CoRR
Sai Praneeth Karimireddy, Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
2018 J jnl
EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings.
CoRR
Kamil Bennani-Smires, Claudiu Musat, Martin Jaggi, Andreea Hossmann, Michael Baeriswyl
2018 J jnl
End-to-End DNN Training with Block Floating Point Arithmetic.
CoRR
Mario Drumond, Tao Lin, Martin Jaggi, Babak Falsafi
2018 J jnl
Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients.
CoRR
Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
2018 A* conf
On Matching Pursuit and Coordinate Descent.
ICML
Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy, Gunnar Rätsch, Bernhard Schölkopf, Sebastian U. Stich, Martin Jaggi
2018 J jnl
Optimal Affine-Invariant Smooth Minimization Algorithms.
SIAM J. Optim.
Alexandre d'Aspremont, Cristóbal Guzmán, Martin Jaggi
2018 J jnl
Revisiting First-Order Convex Optimization Over Linear Spaces.
CoRR
Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy, Gunnar Rätsch, Bernhard Schölkopf, Sebastian U. Stich, Martin Jaggi
2018 B conf
Simple Unsupervised Keyphrase Extraction using Sentence Embeddings.
CoNLL
Kamil Bennani-Smires, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl, Martin Jaggi
2018 A* conf
Sparsified SGD with Memory.
NeurIPS
Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi
2018 J jnl
Sparsified SGD with Memory.
CoRR
Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi
2018 A* conf
Training DNNs with Hybrid Block Floating Point.
NeurIPS
Mario Drumond, Tao Lin, Martin Jaggi, Babak Falsafi
2018 — conf
Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features.
NAACL-HLT
Matteo Pagliardini, Prakhar Gupta, Martin Jaggi
2018 J jnl
Wasserstein is all you need.
CoRR
Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi
2017 A conf
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe.
AISTATS
Francesco Locatello, Rajiv Khanna, Michael Tschannen, Martin Jaggi
2017 J jnl
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe.
CoRR
Francesco Locatello, Rajiv Khanna, Michael Tschannen, Martin Jaggi
2017 J jnl
An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning.
CoRR
Chenxin Ma, Martin Jaggi, Frank E. Curtis, Nathan Srebro, Martin Takác
2017 A* conf
Approximate Steepest Coordinate Descent.
ICML
Sebastian U. Stich, Anant Raj, Martin Jaggi
2017 J jnl
Approximate Steepest Coordinate Descent.
CoRR
Sebastian U. Stich, Anant Raj, Martin Jaggi
2017 J jnl
CoCoA: A General Framework for Communication-Efficient Distributed Optimization.
J. Mach. Learn. Res.
Virginia Smith, Simone Forte, Chenxin Ma, Martin Takác, Michael I. Jordan, Martin Jaggi
2017 J jnl
Distributed optimization with arbitrary local solvers.
Optim. Methods Softw.
Chenxin Ma, Jakub Konecný, Martin Jaggi, Virginia Smith, Michael I. Jordan, Peter Richtárik, Martin Takác
2017 — conf
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems.
NIPS
Celestine Dünner, Thomas P. Parnell, Martin Jaggi
2017 J jnl
Efficient Use of Limited-Memory Resources to Accelerate Linear Learning.
CoRR
Celestine Dünner, Thomas P. Parnell, Martin Jaggi
2017 A conf
Faster Coordinate Descent via Adaptive Importance Sampling.
AISTATS
Dmytro Perekrestenko, Volkan Cevher, Martin Jaggi
2017 J jnl
Faster Coordinate Descent via Adaptive Importance Sampling.
CoRR
Dmytro Perekrestenko, Volkan Cevher, Martin Jaggi
2017 — conf
Generating Steganographic Text with LSTMs.
ACL (Student Research Workshop)
Tina Fang, Martin Jaggi, Katerina J. Argyraki
2017 J jnl
Generating Steganographic Text with LSTMs.
CoRR
Tina Fang, Martin Jaggi, Katerina J. Argyraki
2017 — conf
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees.
NIPS
Francesco Locatello, Michael Tschannen, Gunnar Rätsch, Martin Jaggi
2017 J jnl
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees.
CoRR
Francesco Locatello, Michael Tschannen, Gunnar Rätsch, Martin Jaggi
2017 J jnl
Learning Aerial Image Segmentation From Online Maps.
IEEE Trans. Geosci. Remote. Sens.
Pascal Kaiser, Jan Dirk Wegner, Aurélien Lucchi, Martin Jaggi, Thomas Hofmann, Konrad Schindler
2017 J jnl
Learning Aerial Image Segmentation from Online Maps.
CoRR
Pascal Kaiser, Jan Dirk Wegner, Aurélien Lucchi, Martin Jaggi, Thomas Hofmann, Konrad Schindler
2017 A* conf
Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification.
WWW
Jan Deriu, Aurélien Lucchi, Valeria De Luca, Aliaksei Severyn, Simon Müller, Mark Cieliebak, Thomas Hofmann, Martin Jaggi
2017 J jnl
Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification.
CoRR
Jan Deriu, Aurélien Lucchi, Valeria De Luca, Aliaksei Severyn, Simon Müller, Mark Cieliebak, Thomas Hofmann, Martin Jaggi
2017 — conf
Safe Adaptive Importance Sampling.
NIPS
Sebastian U. Stich, Anant Raj, Martin Jaggi
2017 J jnl
Safe Adaptive Importance Sampling.
CoRR
Sebastian U. Stich, Anant Raj, Martin Jaggi
2017 J jnl
Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features.
CoRR
Matteo Pagliardini, Prakhar Gupta, Martin Jaggi
2017 J jnl
Unsupervised robust nonparametric learning of hidden community properties.
CoRR
Mikhail A. Langovoy, Akhilesh Gotmare, Martin Jaggi, Suvrit Sra
2016 — conf
Audio Based Bird Species Identification using Deep Learning Techniques.
CLEF (Working Notes)
Elias Sprengel, Martin Jaggi, Yannic Kilcher, Thomas Hofmann
2016 J jnl
CoCoA: A General Framework for Communication-Efficient Distributed Optimization.
CoRR
Virginia Smith, Simone Forte, Chenxin Ma, Martin Takác, Michael I. Jordan, Martin Jaggi
2016 A* conf
Primal-Dual Rates and Certificates.
ICML
Celestine Dünner, Simone Forte, Martin Takác, Martin Jaggi
2016 J jnl
Primal-Dual Rates and Certificates.
CoRR
Celestine Dünner, Simone Forte, Martin Takác, Martin Jaggi
2016 J jnl
Pursuits in Structured Non-Convex Matrix Factorizations.
CoRR
Rajiv Khanna, Michael Tschannen, Martin Jaggi
2016 J jnl
Screening Rules for Convex Problems.
CoRR
Anant Raj, Jakob Olbrich, Bernd Gärtner, Bernhard Schölkopf, Martin Jaggi
2016 — conf
SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision.
SemEval@NAACL-HLT
Jan Deriu, Maurice Gonzenbach, Fatih Uzdilli, Aurélien Lucchi, Valeria De Luca, Martin Jaggi
2015 A* conf
Adding vs. Averaging in Distributed Primal-Dual Optimization.
ICML
Chenxin Ma, Virginia Smith, Martin Jaggi, Michael I. Jordan, Peter Richtárik, Martin Takác
2015 J jnl
Adding vs. Averaging in Distributed Primal-Dual Optimization.
CoRR
Chenxin Ma, Virginia Smith, Martin Jaggi, Michael I. Jordan, Peter Richtárik, Martin Takác
2015 J jnl
Distributed Optimization with Arbitrary Local Solvers.
CoRR
Chenxin Ma, Jakub Konecný, Martin Jaggi, Virginia Smith, Michael I. Jordan, Peter Richtárik, Martin Takác
2015 J jnl
L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework.
CoRR
Virginia Smith, Simone Forte, Michael I. Jordan, Martin Jaggi
2015 — conf
On the Global Linear Convergence of Frank-Wolfe Optimization Variants.
NIPS
Simon Lacoste-Julien, Martin Jaggi
2015 J jnl
On the Global Linear Convergence of Frank-Wolfe Optimization Variants.
CoRR
Simon Lacoste-Julien, Martin Jaggi
2015 — conf
Swiss-Chocolate: Combining Flipout Regularization and Random Forests with Artificially Built Subsystems to Boost Text-Classification for Sentiment.
SemEval@NAACL-HLT
Fatih Uzdilli, Martin Jaggi, Dominic Egger, Pascal Julmy, Leon Derczynski, Mark Cieliebak
2014 — conf
Communication-Efficient Distributed Dual Coordinate Ascent.
NIPS
Martin Jaggi, Virginia Smith, Martin Takác, Jonathan Terhorst, Sanjay Krishnan, Thomas Hofmann, Michael I. Jordan
2014 J jnl
Communication-Efficient Distributed Dual Coordinate Ascent.
CoRR
Martin Jaggi, Virginia Smith, Martin Takác, Jonathan Terhorst, Sanjay Krishnan, Thomas Hofmann, Michael I. Jordan
2014 — conf
Swiss-Chocolate: Sentiment Detection using Sparse SVMs and Part-Of-Speech n-Grams.
SemEval@COLING
Martin Jaggi, Fatih Uzdilli, Mark Cieliebak
2013 J jnl
An Equivalence between the Lasso and Support Vector Machines
CoRR
Martin Jaggi
2013 — conf
Block-Coordinate Frank-Wolfe Optimization for Structural SVMs.
ICML (1)
Simon Lacoste-Julien, Martin Jaggi, Mark Schmidt, Patrick Pletscher
2013 — conf
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization.
ICML (1)
Martin Jaggi
2012 J jnl
An Exponential Lower Bound on the Complexity of Regularization Paths.
J. Comput. Geom.
Bernd Gärtner, Martin Jaggi, Clément Maria
2012 J jnl
Approximating parameterized convex optimization problems.
ACM Trans. Algorithms
Joachim Giesen, Martin Jaggi, Sören Laue
2012 A conf
Optimizing over the Growing Spectrahedron.
ESA
Joachim Giesen, Martin Jaggi, Sören Laue
2012 A conf
Regularization Paths with Guarantees for Convex Semidefinite Optimization.
AISTATS
Joachim Giesen, Martin Jaggi, Sören Laue
2012 J jnl
Stochastic Block-Coordinate Frank-Wolfe Optimization for Structural SVMs
CoRR
Simon Lacoste-Julien, Martin Jaggi, Mark Schmidt, Patrick Pletscher
2011 J jnl
Convex Optimization without Projection Steps
CoRR
Martin Jaggi
2011 — —
Sparse Convex Optimization Methods for Machine Learning.
Martin Jaggi
2010 A* conf
A Simple Algorithm for Nuclear Norm Regularized Problems.
ICML
Martin Jaggi, Marek Sulovský
2010 — conf
Approximating Parameterized Convex Optimization Problems.
ESA (1)
Joachim Giesen, Martin Jaggi, Sören Laue
2009 J jnl
A Combinatorial Algorithm to Compute Regularization Paths
CoRR
Bernd Gärtner, Joachim Giesen, Martin Jaggi, Torsten Welsch
2009 J jnl
An Exponential Lower Bound on the Complexity of Regularization Paths
CoRR
Bernd Gärtner, Joachim Giesen, Martin Jaggi
2009 — conf
Coresets for polytope distance.
SCG
Bernd Gärtner, Martin Jaggi