Filip Hanzely - RankMe

35 papers A* 7A 4Journal 23

Year	Rank	Type	Title / Venue / Authors
2023	J	`jnl`	Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques. Trans. Mach. Learn. Res. Filip Hanzely, Boxin Zhao, Mladen Kolar
2022	J	`jnl`	Personalized Federated Learning with Multiple Known Clusters. CoRR Boxiang Lyu, Filip Hanzely, Mladen Kolar
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	J	`jnl`	Accelerated Bregman proximal gradient methods for relatively smooth convex optimization. Comput. Optim. Appl. Filip Hanzely, Peter Richtárik, Lin Xiao
2021	J	`jnl`	Fastest rates for stochastic mirror descent methods. Comput. Optim. Appl. Filip Hanzely, Peter Richtárik
2021	A	`conf`	Local SGD: Unified Theory and New Efficient Methods. AISTATS Eduard Gorbunov, Filip Hanzely, Peter Richtárik
2021	J	`jnl`	Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques. CoRR Filip Hanzely, Boxin Zhao, Mladen Kolar
2021	A*	`conf`	Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization. NeurIPS Mher Safaryan, Filip Hanzely, Peter Richtárik
2021	J	`jnl`	Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization. CoRR Mher Safaryan, Filip Hanzely, Peter Richtárik
2020	A	`conf`	99% of Worker-Master Communication in Distributed Optimization Is Not Needed. UAI Konstantin Mishchenko, Filip Hanzely, Peter Richtárik
2020	A	`conf`	A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent. AISTATS Eduard Gorbunov, Filip Hanzely, Peter Richtárik
2020	J	`jnl`	Best Pair Formulation & Accelerated Scheme for Non-Convex Principal Component Pursuit. IEEE Trans. Signal Process. Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik
2020	J	`jnl`	Federated Learning of a Mixture of Global and Local Models. CoRR Filip Hanzely, Peter Richtárik
2020	J	`jnl`	Local SGD: Unified Theory and New Efficient Methods. CoRR Eduard Gorbunov, Filip Hanzely, Peter Richtárik
2020	A*	`conf`	Lower Bounds and Optimal Algorithms for Personalized Federated Learning. NeurIPS Filip Hanzely, Slavomír Hanzely, Samuel Horváth, Peter Richtárik
2020	J	`jnl`	Lower Bounds and Optimal Algorithms for Personalized Federated Learning. CoRR Filip Hanzely, Slavomír Hanzely, Samuel Horváth, Peter Richtárik
2020	J	`jnl`	Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters. CoRR Filip Hanzely
2020	—	`—`	Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters. Filip Hanzely
2020	A*	`conf`	Stochastic Subspace Cubic Newton Method. ICML Filip Hanzely, Nikita Doikov, Yurii E. Nesterov, Peter Richtárik
2020	J	`jnl`	Stochastic Subspace Cubic Newton Method. CoRR Filip Hanzely, Nikita Doikov, Peter Richtárik, Yurii E. Nesterov
2020	A*	`conf`	Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems. ICML Filip Hanzely, Dmitry Kovalev, Peter Richtárik
2020	J	`jnl`	Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems. CoRR Filip Hanzely, Dmitry Kovalev, Peter Richtárik
2019	J	`jnl`	99% of Parallel Optimization is Inevitably a Waste of Time. CoRR Konstantin Mishchenko, Filip Hanzely, Peter Richtárik
2019	A*	`conf`	A Nonconvex Projection Method for Robust PCA. AAAI Aritra Dutta, Filip Hanzely, Peter Richtárik
2019	J	`jnl`	A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion. CoRR Filip Hanzely, Jakub Konecný, Nicolas Loizou, Peter Richtárik, Dmitry Grishchenko
2019	J	`jnl`	A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent. CoRR Eduard Gorbunov, Filip Hanzely, Peter Richtárik
2019	A	`conf`	Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches. AISTATS Filip Hanzely, Peter Richtárik
2019	J	`jnl`	Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit. CoRR Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik
2019	J	`jnl`	One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods. CoRR Filip Hanzely, Peter Richtárik
2018	J	`jnl`	A Nonconvex Projection Method for Robust PCA. CoRR Aritra Dutta, Filip Hanzely, Peter Richtárik
2018	A*	`conf`	Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization. NeurIPS Robert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich
2018	J	`jnl`	Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization. CoRR Robert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich
2018	J	`jnl`	Fastest Rates for Stochastic Mirror Descent Methods. CoRR Filip Hanzely, Peter Richtárik
2018	A*	`conf`	SEGA: Variance Reduction via Gradient Sketching. NeurIPS Filip Hanzely, Konstantin Mishchenko, Peter Richtárik
2018	J	`jnl`	SEGA: Variance Reduction via Gradient Sketching. CoRR Filip Hanzely, Konstantin Mishchenko, Peter Richtárik