Gauthier Gidel

Anastasios Kyrillidis

Trans. Mach. Learn. Res., 2024

Investigating the Benefits of Nonlinear Action Maps in Data-Driven Teleoperation.

[BibT_eX]

[DOI]

CoRR, 2024

General Causal Imputation via Synthetic Interventions.

[BibT_eX]

[DOI]

CoRR, 2024

Performative Prediction on Games and Mechanism Design.

[BibT_eX]

[DOI]

CoRR, 2024

Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences.

[BibT_eX]

[DOI]

CoRR, 2024

Learning diverse attacks on large language models for robust red-teaming and safety tuning.

[BibT_eX]

[DOI]

CoRR, 2024

Efficient Adversarial Training in LLMs with Continuous Attacks.

[BibT_eX]

[DOI]

CoRR, 2024

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space.

[BibT_eX]

[DOI]

CoRR, 2024

In-Context Learning Can Re-learn Forbidden Tasks.

[BibT_eX]

[DOI]

CoRR, 2024

A Persuasive Approach to Combating Misinformation.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise.

[BibT_eX]

[DOI]

Pavel E. Dvurechensky

Peter Richtárik

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features.

[BibT_eX]

[DOI]

Aleksandr Beznosikov

David Dobre

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Synaptic Weight Distributions Depend on the Geometry of Plasticity.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Expected flow networks in stochastic environments and two-player zero-sum games.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

On the Stability of Iterative Retraining of Generative Models on their own Data.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Stochastic Frank-Wolfe: Unified Analysis and Zoo of Special Cases.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Q-learners Can Provably Collude in the Iterated Prisoner's Dilemma.

[BibT_eX]

[DOI]

CoRR, 2023

AI4GCC - Track 3: Consumption and the Challenges of Multi-Agent RL.

[BibT_eX]

[DOI]

Marco Jiralerspong

CoRR, 2023

Omega: Optimistic EMA Gradients.

[BibT_eX]

[DOI]

CoRR, 2023

Raising the Bar for Certified Adversarial Robustness with Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2023

Feature Likelihood Score: Evaluating Generalization of Generative Models Using Samples.

[BibT_eX]

[DOI]

Marco Jiralerspong

Avishek Joey Bose

CoRR, 2023

Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Feature Likelihood Score: Evaluating the Generalization of Generative Models Using Samples.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance.

[BibT_eX]

[DOI]

Pavel E. Dvurechensky

Peter Richtárik

Proceedings of the International Conference on Machine Learning, 2023

Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Adversarial Attacks and Defenses in Large Language Models: Old and New Threats.

[BibT_eX]

[DOI]

Proceedings of the Proceedings on "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops, 2023

Performative Prediction with Neural Networks.

[BibT_eX]

[DOI]

Mehrnaz Mofakhami

Ioannis Mitliagkas

Wojciech Marian Czarnecki

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

On the Limitations of the Elo, Real-World Games are Transitive, not Additive.

[BibT_eX]

[DOI]

Quentin Bertrand

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Extragradient with Positive Momentum is Optimal for Games with Cross-Shaped Jacobian Spectrum.

[BibT_eX]

[DOI]

Junhyung Lyle Kim

Anastasios Kyrillidis

CoRR, 2022

Nesterov Meets Optimism: Rate-Optimal Optimistic-Gradient-Based Method for Stochastic Bilinearly-Coupled Minimax Optimization.

[BibT_eX]

[DOI]

CoRR, 2022

Dissecting adaptive methods in GANs.

[BibT_eX]

[DOI]

CoRR, 2022

Proceedings of the ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts.

[BibT_eX]

[DOI]

CoRR, 2022

Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms.

[BibT_eX]

[DOI]

Marco Jiralerspong

CoRR, 2022

Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization.

[BibT_eX]

[DOI]

CoRR, 2022

The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts.

[BibT_eX]

[DOI]

CoRR, 2022

The Curse of Unrolling: Rate of Differentiating Through Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities.

[BibT_eX]

[DOI]

Eduard Gorbunov

Adrien B. Taylor

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise.

[BibT_eX]

[DOI]

Eduard Gorbunov

Marina Danilova

David Dobre

Pavel E. Dvurechenskii

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Beyond L1: Faster and Better Sparse Models with skglm.

[BibT_eX]

[DOI]

Quentin Bertrand

Quentin Klopfenstein

Pierre-Antoine Bannier

Mathurin Massias

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Only tails matter: Average-Case Universality and Robustness in the Convex Regime.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Online Adversarial Attacks.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Extragradient Method: O(1/K) Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity.

[BibT_eX]

[DOI]

Eduard Gorbunov

Nicolas Loizou

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Stochastic Extragradient: General Analysis and Improved Rates.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Generating Diverse Realistic Laughter for Interactive Art.

[BibT_eX]

[DOI]

CoRR, 2021

Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks.

[BibT_eX]

[DOI]

Manuela Girotti

Ioannis Mitliagkas

CoRR, 2021

On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging.

[BibT_eX]

[DOI]

CoRR, 2021

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

A single gradient step finds adversarial examples on random two-layers neural networks.

[BibT_eX]

[DOI]

Sébastien Bubeck

Yeshwanth Cherapanamjeri

Wojciech Marian Czarnecki

Remi Tachet des Combes

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity.

[BibT_eX]

[DOI]

Marta Garnelo

Proceedings of the AAMAS '21: 20th International Conference on Autonomous Agents and Multiagent Systems, 2021

A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Minimax Theorem for Latent Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets.

[BibT_eX]

[DOI]

Wojciech Marian Czarnecki

David Balduzzi

Marta Garnelo

Yoram Bachrach

CoRR, 2020

Real World Games Look Like Spinning Tops.

[BibT_eX]

[DOI]

Wojciech M. Czarnecki

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Adversarial Example Games.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Linear Lower Bounds and Conditioning of Differentiable Games.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent.

[BibT_eX]

[DOI]

James P. Bailey

Georgios Piliouras

Proceedings of the Conference on Learning Theory, 2020

Accelerating Smooth Games by Manipulating Spectral Shapes.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Lower Bounds and Conditioning of Differentiable Games.

[BibT_eX]

[DOI]

CoRR, 2019

A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games.

[BibT_eX]

[DOI]

CoRR, 2019

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks.

[BibT_eX]

[DOI]

Francis R. Bach

CoRR, 2019

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics.

[BibT_eX]

[DOI]

Giancarlo Kerg

Kyle Goyette

Maximilian Puelma Touzel

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks.

[BibT_eX]

[DOI]

Francis R. Bach

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Reducing Noise in GAN Training with Variance Reduced Extragradient.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Variational Inequality Perspective on Generative Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

Negative Momentum for Improved Game Dynamics.

[BibT_eX]

[DOI]

Reyhane Askari Hemmat

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

A Variational Inequality Perspective on Generative Adversarial Nets.

[BibT_eX]

[DOI]

CoRR, 2018

Adaptive Three Operator Splitting.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Parametric Adversarial Divergences are Good Task Losses for Generative Modeling.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

Frank-Wolfe Splitting via Augmented Lagrangian Method.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017

Adversarial Divergences are Good Task Losses for Generative Modeling.

[BibT_eX]

[DOI]

CoRR, 2017

Frank-Wolfe Algorithms for Saddle Point Problems.

[BibT_eX]

[DOI]

Tony Jebara