Efficient learning in multi-armed bandit mechanisms such as pay-per-clic...
Federated learning (FL) is a common and practical framework for learning...
The projection operation is a critical component in a wide range of
opti...
First-order optimization methods tend to inherently favor certain soluti...
We study the phenomenon of in-context learning (ICL) exhibited by
large ...
In this paper, we consider the sequential decision problem where the goa...
The classical algorithms for online learning and decision-making have th...
The classical Perceptron algorithm of Rosenblatt can be used to find a l...
We develop an algorithmic framework for solving convex optimization prob...
Stochastic gradient descent (SGD) with stochastic momentum is popular in...
Alongside the well-publicized accomplishments of deep neural networks th...
Binary linear classification has been explored since the very early days...
Over-parametrization has become a popular technique in deep learning. It...
Incorporating a so-called "momentum" dynamic in gradient descent methods...
The Heavy Ball Method, proposed by Polyak over five decades ago, is a
fi...
One of the major breakthroughs in deep learning over the past five years...
Existing methods for reducing disparate performance of a classifier acro...
We consider the dynamics of two-player zero-sum games, with the goal of
...
We study the problem of repeated play in a zero-sum game in which the pa...
We study the problem of finding min-max solutions for smooth two-input
o...
We consider the problem of minimizing a smooth convex function by reduci...
We detail our ongoing work in Flint, Michigan to detect pipes made of le...
We consider the use of no-regret algorithms to compute equilibria for
pa...
When the residents of Flint learned that lead had contaminated their wat...
We propose studying GAN training dynamics as regret minimization, which ...
We define a novel family of algorithms for the adversarial multi-armed b...
We design mechanisms for online procurement of data held by strategic ag...
We consider the design of prediction market mechanisms known as automate...