Gintare Karolina Dziugaite

93 papers A* 21A 7B 2Journal 58Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Detoxifying LLMs via Representation Erasure-Based Preference Optimization. CoRR Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, Daniel M. Roy, Gintare Karolina Dziugaite
2026	J	`jnl`	SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning. Trans. Mach. Learn. Res. Riyasat Ohib, Bishal Thapaliya, Gintare Karolina Dziugaite, Jingyu Liu, Vince D. Calhoun, Sergey M. Plis
2025	J	`jnl`	Continual Learning in Vision-Language Models via Aligned Model Merging. CoRR Ghada Sokar, Gintare Karolina Dziugaite, Anurag Arnab, Ahmet Iscen, Pablo Samuel Castro, Cordelia Schmid
2025	J	`jnl`	From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization. CoRR Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger, Gintare Karolina Dziugaite, Michael Curtis Mozer, Eleni Triantafillou
2025	J	`jnl`	Improved Localized Machine Unlearning Through the Lens of Memorization. Trans. Mach. Learn. Res. Reihaneh Torkzadehmahani, Reza Nasirigerdeh, Georgios Kaissis, Daniel Rueckert, Gintare Karolina Dziugaite, Eleni Triantafillou
2025	J	`jnl`	Less is More: Undertraining Experts Improves Model Upcycling. CoRR Stefan Horoi, Guy Wolf, Eugene Belilovsky, Gintare Karolina Dziugaite
2025	A*	`conf`	Leveraging Per-Instance Privacy for Machine Unlearning. ICML Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou, Daniel M. Roy, Gintare Karolina Dziugaite
2025	J	`jnl`	Leveraging Per-Instance Privacy for Machine Unlearning. CoRR Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou, Daniel M. Roy, Gintare Karolina Dziugaite
2025	A*	`conf`	Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization. ICML Phillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite
2025	J	`jnl`	On the Dichotomy Between Privacy and Traceability in ℓ CoRR Sasha Voitovych, Mahdi Haghifam, Idan Attias, Gintare Karolina Dziugaite, Roi Livni, Daniel M. Roy
2025	A*	`conf`	Selective Unlearning via Representation Erasure Using Domain Adversarial Training. ICLR Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, James J. Clark, Daniel M. Roy, Gintare Karolina Dziugaite
2025	J	`jnl`	Soup to go: mitigating forgetting during continual learning with model averaging. CoRR Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle, Sham M. Kakade, Mansheej Paul
2025	A*	`conf`	The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws. ICLR Tian Jin, Ahmed Imtiaz Humayun, Utku Evci, Suvinay Subramanian, Amir Yazdanbakhsh, Dan Alistarh, Gintare Karolina Dziugaite
2025	J	`jnl`	The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws. CoRR Tian Jin, Ahmed Imtiaz Humayun, Utku Evci, Suvinay Subramanian, Amir Yazdanbakhsh, Dan Alistarh, Gintare Karolina Dziugaite
2025	A	`conf`	The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws. AISTATS Gintare Karolina Dziugaite, Daniel M. Roy
2024	J	`jnl`	Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition. CoRR Eleni Triantafillou, Peter Kairouz, Fabian Pedregosa, Jamie Hayes, Meghdad Kurmanji, Kairan Zhao, Vincent Dumoulin, Júlio C. S. Jacques Júnior, Ioannis Mitliagkas, Jun Wan, Lisheng Sun-Hosoya, Sergio Escalera, Gintare Karolina Dziugaite, Peter Triantafillou, Isabelle Guyon
2024	—	`ed.`	Conference on Parsimony and Learning, Hongkong, China, 3-6 January 2024. CPAL Yuejie Chi, Gintare Karolina Dziugaite, Qing Qu, Atlas Wang Wang, Zhihui Zhu
2024	J	`jnl`	Data Selection for Transfer Unlearning. CoRR Nazanin Mohammadi Sepahvand, Vincent Dumoulin, Eleni Triantafillou, Gintare Karolina Dziugaite
2024	J	`jnl`	Dataset Difficulty and the Role of Inductive Bias. CoRR Devin Kwok, Nikhil Anand, Jonathan Frankle, Gintare Karolina Dziugaite, David Rolnick
2024	J	`jnl`	Evaluating Interventional Reasoning Capabilities of Large Language Models. CoRR Tejas Kasetty, Divyat Mahajan, Gintare Karolina Dziugaite, Alexandre Drouin, Dhanya Sridhar
2024	A	`conf`	Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias. AISTATS Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman
2024	J	`jnl`	Improved Localized Machine Unlearning Through the Lens of Memorization. CoRR Reihaneh Torkzadehmahani, Reza Nasirigerdeh, Georgios Kaissis, Daniel Rueckert, Gintare Karolina Dziugaite, Eleni Triantafillou
2024	J	`jnl`	Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization. CoRR Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy
2024	A*	`conf`	Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing. ICML Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy
2024	—	`conf`	Jaxpruner: A Concise Library for Sparsity Research. CPAL Joo Hyung Lee, Wonpyo Park, Nicole Mitchell, Jonathan Pilault, Johan Samir Obando Ceron, Han-Byul Kim, Namhoon Lee, Elias Frantar, Yun Long, Amir Yazdanbakhsh, Woohyun Han, Shivani Agrawal, Suvinay Subramanian, Xin Wang, Sheng-Chun Kao, Xingyao Zhang, Trevor Gale, Aart J. C. Bik, Milen Ferev, Zhonglin Han, Hong-Seok Kim, Yann N. Dauphin, Gintare Karolina Dziugaite, Pablo Samuel Castro, Utku Evci
2024	J	`jnl`	Leveraging Function Space Aggregation for Federated Learning at Scale. Trans. Mach. Learn. Res. Nikita Dhawan, Nicole Mitchell, Zachary Charles, Zachary Garrett, Gintare Karolina Dziugaite
2024	J	`jnl`	Linear Weight Interpolation Leads to Transient Performance Gains. Trans. Mach. Learn. Res. Gaurav Iyer, Gintare Karolina Dziugaite, David Rolnick
2024	J	`jnl`	Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization. CoRR Phillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite
2024	J	`jnl`	Mixture of Experts in a Mixture of RL settings. RLJ Timon Willi, Johan S. Obando-Ceron, Jakob Nicolaus Foerster, Gintare Karolina Dziugaite, Pablo Samuel Castro
2024	A*	`conf`	Mixtures of Experts Unlock Parameter Scaling for Deep RL. ICML Johan S. Obando-Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob Nicolaus Foerster, Gintare Karolina Dziugaite, Doina Precup, Pablo Samuel Castro
2024	J	`jnl`	Mixtures of Experts Unlock Parameter Scaling for Deep RL. CoRR Johan S. Obando-Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob N. Foerster, Gintare Karolina Dziugaite, Doina Precup, Pablo Samuel Castro
2024	—	`conf`	Simultaneous Linear Connectivity of Neural Networks Modulo Permutation. ECML/PKDD (7) Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick, Gintare Karolina Dziugaite
2024	J	`jnl`	Simultaneous linear connectivity of neural networks modulo permutation. CoRR Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick, Gintare Karolina Dziugaite
2024	A*	`conf`	The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning. ICLR Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite
2024	J	`jnl`	The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse. CoRR Ekansh Sharma, Daniel M. Roy, Gintare Karolina Dziugaite
2024	J	`jnl`	Torque-Aware Momentum. CoRR Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Gintare Karolina Dziugaite, Razvan Pascanu, Sarath Chandar
2024	J	`jnl`	Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method. CoRR Teodora Baluta, Pascal Lamblin, Daniel Tarlow, Fabian Pedregosa, Gintare Karolina Dziugaite
2024	J	`jnl`	Unmasking Efficiency: Learning Salient Sparse Models in Non-IID Federated Learning. CoRR Riyasat Ohib, Bishal Thapaliya, Gintare Karolina Dziugaite, Jingyu Liu, Vince D. Calhoun, Sergey M. Plis
2023	J	`jnl`	Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias. CoRR Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman
2023	J	`jnl`	Leveraging Function Space Aggregation for Federated Learning at Scale. CoRR Nikita Dhawan, Nicole Mitchell, Zachary Charles, Zachary Garrett, Gintare Karolina Dziugaite
2023	B	`conf`	Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization. ALT Mahdi Haghifam, Borja Rodríguez Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite
2023	J	`jnl`	The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning. CoRR Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite
2023	A*	`conf`	Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? ICLR Mansheej Paul, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite
2022	J	`jnl`	Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization. CoRR Mahdi Haghifam, Borja Rodríguez Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite
2022	A*	`conf`	Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. NeurIPS Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite
2022	J	`jnl`	Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. CoRR Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite
2022	A*	`conf`	Pruning's Effect on Generalization Through the Lens of Training and Regularization. NeurIPS Tian Jin, Michael Carbin, Daniel M. Roy, Jonathan Frankle, Gintare Karolina Dziugaite
2022	J	`jnl`	Pruning's Effect on Generalization Through the Lens of Training and Regularization. CoRR Tian Jin, Michael Carbin, Daniel M. Roy, Jonathan Frankle, Gintare Karolina Dziugaite
2022	J	`jnl`	The Effect of Data Dimensionality on Neural Network Prunability. CoRR Zachary Ankner, Alex Renda, Gintare Karolina Dziugaite, Jonathan Frankle, Tian Jin
2022	B	`conf`	Understanding Generalization via Leave-One-Out Conditional Mutual Information. ISIT Mahdi Haghifam, Shay Moran, Daniel M. Roy, Gintare Karolina Dziugaite
2022	J	`jnl`	Understanding Generalization via Leave-One-Out Conditional Mutual Information. CoRR Mahdi Haghifam, Shay Moran, Daniel M. Roy, Gintare Karolina Dziugaite
2022	J	`jnl`	Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? CoRR Mansheej Paul, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite
2021	A*	`conf`	Deep Learning on a Data Diet: Finding Important Examples Early in Training. NeurIPS Mansheej Paul, Surya Ganguli, Gintare Karolina Dziugaite
2021	J	`jnl`	Deep Learning on a Data Diet: Finding Important Examples Early in Training. CoRR Mansheej Paul, Surya Ganguli, Gintare Karolina Dziugaite
2021	A	`conf`	On the role of data in PAC-Bayes. AISTATS Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Gabriel Arpino, Daniel M. Roy
2021	J	`jnl`	Probabilistic fine-tuning of pruning masks and PAC-Bayes self-bounded learning. CoRR Soufiane Hayou, Bobby He, Gintare Karolina Dziugaite
2021	A*	`conf`	Pruning Neural Networks at Initialization: Why Are We Missing the Mark? ICLR Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
2021	A*	`conf`	Towards a Unified Information-Theoretic Framework for Generalization. NeurIPS Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy
2021	J	`jnl`	Towards a Unified Information-Theoretic Framework for Generalization. CoRR Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy
2020	A*	`conf`	Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel. NeurIPS Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli
2020	J	`jnl`	Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel. CoRR Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli
2020	J	`jnl`	Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability. CoRR Gintare Karolina Dziugaite, Shai Ben-David, Daniel M. Roy
2020	A*	`conf`	In Defense of Uniform Convergence: Generalization via Derandomization with an Application to Interpolating Predictors. ICML Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy
2020	J	`jnl`	In Search of Robust Measures of Generalization. CoRR Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy
2020	A*	`conf`	In search of robust measures of generalization. NeurIPS Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy
2020	A*	`conf`	Linear Mode Connectivity and the Lottery Ticket Hypothesis. ICML Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
2020	—	`conf`	Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning. NeurIPS (Competition and Demos) Yiding Jiang, Parth Natekar, Manik Sharma, Sumukh K. Aithal, Dhruva Kashyap, Natarajan Subramanyam, Carlos Lassance, Daniel M. Roy, Gintare Karolina Dziugaite, Suriya Gunasekar, Isabelle Guyon, Pierre Foret, Scott Yak, Hossein Mobahi, Behnam Neyshabur, Samy Bengio
2020	J	`jnl`	NeurIPS 2020 Competition: Predicting Generalization in Deep Learning. CoRR Yiding Jiang, Pierre Foret, Scott Yak, Daniel M. Roy, Hossein Mobahi, Gintare Karolina Dziugaite, Samy Bengio, Suriya Gunasekar, Isabelle Guyon, Behnam Neyshabur
2020	J	`jnl`	On the Information Complexity of Proper Learners for VC Classes in the Realizable Case. CoRR Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy
2020	J	`jnl`	On the role of data in PAC-Bayes bounds. CoRR Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Daniel M. Roy
2020	J	`jnl`	Pruning Neural Networks at Initialization: Why are We Missing the Mark? CoRR Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
2020	J	`jnl`	RelatIF: Identifying Explanatory Training Examples via Relative Influence. CoRR Elnaz Barshan, Marc-Etienne Brunet, Gintare Karolina Dziugaite
2020	A	`conf`	RelatIF: Identifying Explanatory Training Samples via Relative Influence. AISTATS Elnaz Barshan, Marc-Etienne Brunet, Gintare Karolina Dziugaite
2020	A*	`conf`	Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms. NeurIPS Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M. Roy, Gintare Karolina Dziugaite
2020	J	`jnl`	Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms. CoRR Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M. Roy, Gintare Karolina Dziugaite
2020	A	`conf`	Stochastic Neural Network with Kronecker Flow. AISTATS Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron C. Courville
2019	J	`jnl`	In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors. CoRR Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy
2019	A*	`conf`	Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. NeurIPS Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy
2019	J	`jnl`	Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. CoRR Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy
2019	J	`jnl`	Linear Mode Connectivity and the Lottery Ticket Hypothesis. CoRR Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
2019	—	`—`	Revisiting generalization for deep learning: PAC-Bayes, flat minima, and generative models. Gintare Karolina Dziugaite
2019	J	`jnl`	Stochastic Neural Network with Kronecker Flow. CoRR Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron C. Courville
2019	J	`jnl`	The Lottery Ticket Hypothesis at Scale. CoRR Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
2018	A*	`conf`	Data-dependent PAC-Bayes priors via differential privacy. NeurIPS Gintare Karolina Dziugaite, Daniel M. Roy
2018	J	`jnl`	Data-dependent PAC-Bayes priors via differential privacy. CoRR Gintare Karolina Dziugaite, Daniel M. Roy
2018	A*	`conf`	Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors. ICML Gintare Karolina Dziugaite, Daniel M. Roy
2017	A	`conf`	Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data. UAI Gintare Karolina Dziugaite, Daniel M. Roy
2017	J	`jnl`	Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data. CoRR Gintare Karolina Dziugaite, Daniel M. Roy
2017	J	`jnl`	Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy. CoRR Gintare Karolina Dziugaite, Daniel M. Roy
2016	J	`jnl`	A study of the effect of JPG compression on adversarial images. CoRR Gintare Karolina Dziugaite, Zoubin Ghahramani, Daniel M. Roy
2015	J	`jnl`	Neural Network Matrix Factorization. CoRR Gintare Karolina Dziugaite, Daniel M. Roy
2015	A	`conf`	Training generative neural networks via Maximum Mean Discrepancy optimization. UAI Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani
2015	J	`jnl`	Training generative neural networks via Maximum Mean Discrepancy optimization. CoRR Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani