157 citations · 529 across the 78 of their papers we have counts for
15 papers · 1 filter
When is Momentum Extragradient Optimal? A Polynomial-Based Analysis
Junhyung Lyle Kim, Gauthier Gidel, Anastasios Kyrillidis +1
The extragradient method has gained popularity due to its robust convergence properties for differentiable games. Unlike single-objective optimization, game dynamics involve comple…
Dissecting adaptive methods in GANs
Samy Jelassi, David Dobre, Arthur Mensch +2
Adaptive methods are a crucial component widely used for training generative adversarial networks (GANs). While there has been some work to pinpoint the "marginal value of adaptive…
Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
Chris Junchi Li, Angela Yuan, Gauthier Gidel +2
We propose a new first-order optimization algorithm -- AcceleratedGradient-OptimisticGradient (AG-OG) Descent Ascent -- for separable convex-concave minimax optimization. The main…
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity
Eduard Gorbunov, Adrien Taylor, Samuel Horváth +1
Algorithms for min-max optimization and variational inequalities are often studied under monotonicity assumptions. Motivated by non-monotone machine learning applications, we follo…
The Curse of Unrolling: Rate of Differentiating Through Optimization
Damien Scieur, Quentin Bertrand, Gauthier Gidel +1
Computing the Jacobian of the solution of an optimization problem is a central problem in machine learning, with applications in hyperparameter optimization, meta-learning, optimiz…
Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms
Marco Jiralerspong, Gauthier Gidel
We describe our approach for the generative emotional vocal burst task (ExVo Generate) of the ICML Expressive Vocalizations Competition. We train a conditional StyleGAN2 architectu…
Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime
Leonardo Cunha, Gauthier Gidel, Fabian Pedregosa +2
The recently developed average-case analysis of optimization methods allows a more fine-grained and representative convergence analysis than usual worst-case results. In exchange,…
On the Limitations of Elo: Real-World Games, are Transitive, not Additive
Quentin Bertrand, Wojciech Marian Czarnecki, Gauthier Gidel
Real-world competitive games, such as chess, go, or StarCraft II, rely on Elo models to measure the strength of their players. Since these games are not fully transitive, using Elo…
Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization
Simon S. Du, Gauthier Gidel, Michael I. Jordan +1
We consider the smooth convex-concave bilinearly-coupled saddle-point problem, , where…
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
Damien Ferbach, Christos Tsirigotis, Gauthier Gidel +2
The Strong Lottery Ticket Hypothesis (SLTH) stipulates the existence of a subnetwork within a sufficiently overparameterized (dense) neural network that -- when initialized randoml…
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
Eduard Gorbunov, Marina Danilova, David Dobre +3
Stochastic first-order methods such as Stochastic Extragradient (SEG) or Stochastic Gradient Descent-Ascent (SGDA) for solving smooth minimax problems and, more generally, variatio…
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
Eduard Gorbunov, Samuel Horváth, Peter Richtárik +1
Byzantine-robustness has been gaining a lot of attention due to the growth of the interest in collaborative and federated learning. However, many fruitful directions, such as the u…
Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities
Eduard Gorbunov, Adrien Taylor, Gauthier Gidel
The Past Extragradient (PEG) [Popov, 1980] method, also known as the Optimistic Gradient method, has known a recent gain in interest in the optimization community with the emergenc…
The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts
Alice Baird, Panagiotis Tzirakis, Gauthier Gidel +7
The ICML Expressive Vocalization (ExVo) Competition is focused on understanding and generating vocal bursts: laughs, gasps, cries, and other non-verbal vocalizations that are centr…
Beyond L1: Faster and Better Sparse Models with skglm
Quentin Bertrand, Quentin Klopfenstein, Pierre-Antoine Bannier +2
We propose a new fast algorithm to estimate any sparse generalized linear model with convex or non-convex separable penalties. Our algorithm is able to solve problems with millions…