Search Results for author:
Found 18 papers, 5 papers with code
Learning Variational Inequalities from Data: Fast Generalization Rates under Strong Monotonicity
Variational inequalities (VIs) are a broad class of optimization problems encompassing machine learning problems ranging from standard convex minimization to more complex scenarios like min-max optimization and computing the equilibria of multi-player games.
On the Hypomonotone Class of Variational Inequalities
This paper studies the behavior of the extragradient algorithm when applied to hypomonotone operators, a class of problems that extends beyond the classical monotone setting.
Variational Inequality Methods for Multi-Agent Reinforcement Learning: Performance and Stability Gains
We present a VI reformulation of the actor-critic algorithm for both single- and multi-agent settings.
A Primal-Dual Approach to Solving Variational Inequalities with General Constraints
We prove the convergence of this method and show that the gap function of the last iterate of the method decreases at a rate of $O(\frac{1}{\sqrt{K}})$ when the operator is $L$-Lipschitz and monotone.
Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata
Algorithms that solve zero-sum games, multi-objective agent objectives, or, more generally, variational inequality (VI) problems are notoriously unstable on general problems.
Solving Constrained Variational Inequalities via a First-order Interior Point-based Method
We provide convergence guarantees for ACVI in two general classes of problems: (i) when the operator is $\xi$-monotone, and (ii) when it is monotone, some constraints are active and the game is not purely rotational.
Improving Generalization via Uncertainty Driven Perturbations
We show that UDP is guaranteed to achieve the maximum margin decision boundary on linear models and that it notably increases it on challenging simulated datasets.
Last-Iterate Convergence of Saddle-Point Optimizers via High-Resolution Differential Equations
However, the convergence properties of these methods are qualitatively different, even on simple bilinear games.
The Peril of Popular Deep Learning Uncertainty Estimation Methods
Secondly, we show on a 2D toy example that both BNNs and MCDropout do not give high uncertainty estimates on OOD samples.
Improved Generalization-Robustness Trade-off via Uncertainty Targeted Attacks
The deep learning models' sensitivity to small input perturbations raises security concerns and limits their use for applications where reliability is critical.
Semantic Perturbations with Normalizing Flows for Improved Generalization
We find that our latent adversarial perturbations adaptive to the classifier throughout its training are most effective, yielding the first test accuracy improvement results on real-world datasets -- CIFAR-10/100 -- via latent-space perturbations.
Convening during COVID-19: Lessons learnt from organizing virtual workshops in 2020
This report is an account of the authors' experiences as organizers of WiML's "Un-Workshop" event at ICML 2020.
Taming GANs with Lookahead-Minmax
Generative Adversarial Networks are notoriously challenging to train.
Reducing Noise in GAN Training with Variance Reduced Extragradient
We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can prevent the convergence of standard game optimization methods, while the batch version converges.
WILDTRACK: A Multi-Camera HD Dataset for Dense Unscripted Pedestrian Detection
People detection methods are highly sensitive to occlusions between pedestrians, which are extremely frequent in many situations where cameras have to be mounted at a limited height.
SGAN: An Alternative Training of Generative Adversarial Networks
The Generative Adversarial Networks (GANs) have demonstrated impressive performance for data synthesis, and are now used in a wide range of computer vision tasks.
The WILDTRACK Multi-Camera Person Dataset
People detection methods are highly sensitive to the perpetual occlusions among the targets.
Deep Multi-camera People Detection
The former does not exploit joint information, whereas the latter deals with ambiguous input due to the foreground blobs becoming more and more interconnected as the number of targets increases.
