The AI4GCC competition presents a bold step forward in the direction of
...
Most learning algorithms in machine learning rely on gradient descent to...
Certified defenses against adversarial attacks offer formal guarantees o...
The Frank-Wolfe (FW) method is a popular approach for solving optimizati...
Performative prediction is a framework for learning models that influenc...
Deep generative models have demonstrated the ability to generate complex...
The extragradient method has recently gained increasing attention, due t...
We provide a novel first-order optimization algorithm for bilinearly-cou...
Adaptive methods are a crucial component widely used for training genera...
Computing the Jacobian of the solution of an optimization problem is a
c...
This is the Proceedings of the ICML Expressive Vocalization (ExVo)
Compe...
We describe our approach for the generative emotional vocal burst task (...
Real-world competitive games, such as chess, go, or StarCraft II, rely o...
The recently developed average-case analysis of optimization methods all...
We consider the smooth convex-concave bilinearly-coupled saddle-point
pr...
The Strong Lottery Ticket Hypothesis (SLTH) stipulates the existence of ...
Byzantine-robustness has been gaining a lot of attention due to the grow...
The ICML Expressive Vocalization (ExVo) Competition is focused on
unders...
We propose a new fast algorithm to estimate any sparse generalized linea...
The Stochastic Extragradient (SEG) method is one of the most popular
alg...
We propose an interactive art project to make those rendered invisible b...
We theoretically analyze the Feedback Alignment (FA) algorithm, an effic...
Extragradient method (EG) Korpelevich [1976] is one of the most popular
...
Strategic diversity is often essential in games: in multi-player games, ...
Two of the most prominent algorithms for solving unconstrained smooth ga...
We study the stochastic bilinear minimax optimization problem, presentin...
Daniely and Schacham recently showed that gradient descent finds adversa...
Adversarial attacks expose important vulnerabilities of deep learning mo...
The existence of adversarial examples capable of fooling trained neural
...
This paper investigates the geometrical properties of real world games (...
Adversarial training, a special case of multi-objective optimization, is...
We use matrix iteration theory to characterize acceleration in smooth ga...
Gradient descent is arguably one of the most popular online optimization...
Many recent machine learning tools rely on differentiable game formulati...
We consider differentiable games: multi-objective minimization problems,...
Generative adversarial networks have been very successful in generative
...
A recent strategy to circumvent the exploding and vanishing gradient pro...
Recent works have shown that stochastic gradient descent (SGD) achieves ...
When optimizing over-parameterized models, such as deep neural networks,...
Using large mini-batches when training generative adversarial networks (...
Games generalize the optimization paradigm by introducing different obje...
Minimizing a function over an intersection of convex sets is an importan...
We propose and analyze a novel adaptive step size variant of the Davis-Y...
Stability has been a recurrent issue in training generative adversarial
...
Generative modeling of high dimensional data like images is a notoriousl...
We extend the Frank-Wolfe (FW) optimization algorithm to solve constrain...