• Publications
  • Influence
The complexity of computing a Nash equilibrium
TLDR
This proof uses ideas from the recently-established equivalence between polynomial time solvability of normal form games and graphical games, establishing that these kinds of games can simulate a PPAD-complete class of Brouwer functions.
Training GANs with Optimism
TLDR
This work addresses the issue of limit cycling behavior in training Generative Adversarial Networks and proposes the use of Optimistic Mirror Decent (OMD) for training Wasserstein GANs and introduces a new algorithm, Optimistic Adam, which is an optimistic variant of Adam.
The Complexity of Computing a Nash Equilibrium
TLDR
It is shown that finding a Nash equilibrium in three-player games is indeed PPAD-complete; and this result is resolved by a reduction from Brouwer's problem, thus establishing that the two problems are computationally equivalent.
The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
TLDR
This work characterize the limit points of two basic first order methods, namely Gradient Descent/Ascent (GDA) and Optimistic Gradients Descent Ascent (OGDA), and shows that both dynamics avoid unstable critical points for almost all initializations.
Optimal Testing for Properties of Distributions
TLDR
This work provides a general approach via which sample-optimal and computationally efficient testers for discrete log-concave and monotone hazard rate distributions are obtained.
The Robust Manifold Defense: Adversarial Training using Generative Models
We propose a new type of attack for finding adversarial examples for image classifiers. Our method exploits spanners, i.e. deep neural networks whose input space is low-dimensional and whose output
Progress in approximate nash equilibria
TLDR
A polynomial algorithm is given for computing an ε-approximate Nash equilibrium in 2-player games with ε ≈ .38; the algorithm computes equilibria with arbitrarily large supports.
Strong Duality for a Multiple-Good Monopolist
TLDR
The framework provides a duality-based framework for revenue maximization in a multiple-good monopoly and proves that grand-bundling mechanisms are optimal if and only if two stochastic dominance conditions hold between specific measures induced by the buyer's type distribution.
An algorithmic characterization of multi-dimensional mechanisms
TLDR
The results provide a characterization of feasible, Bayesian Incentive Compatible mechanisms in multi-item multi-bidder settings, and give a proper generalization of Border's Theorem for a broader class of feasibility constraints, including the intersection of any two matroids.
...
1
2
3
4
5
...