We show that many machine learning goals can be expressed as “rate constraints” on a
model's predictions. We study the problem of training non-convex models subject to these …

Recently, Daskalakis, Fishelson, and Golowich (DFG)(NeurIPS '21) showed that if all agents
in a multi-player general-sum normal-form game employ Optimistic Multiplicative Weights …

In recent years, constrained optimization has become increasingly relevant to the machine
learning community, with applications including Neyman-Pearson classification, robust …

Classifiers can be trained with data-dependent constraints to satisfy fairness goals, reduce
churn, achieve a targeted false positive rate, or other policy goals. We study the …

We consider a number of questions related to tradeoffs between reward and regret in
repeated gameplay between two agents. To facilitate this, we introduce a notion of …

Abstract While Online Gradient Descent and other no-regret learning procedures are known
to efficiently converge to a coarse correlated equilibrium in games where each agent's utility …

In this paper we establish efficient and\emph {uncoupled} learning dynamics so that, when
employed by all players in a general-sum multiplayer game, the\emph {swap regret} of each …

The existence of simple, uncoupled no-regret dynamics that converge to correlated
equilibria in normal-form games is a celebrated result in the theory of multi-agent systems …

Recent breakthrough results by Dagan, Daskalakis, Fishelson and Golowich [2023] and
Peng and Rubinstein [2023] established an efficient algorithm attaining at most $\epsilon …

While extensive-form games (EFGs) can be converted into normal-form games (NFGs),
doing so comes at the cost of an exponential blowup of the strategy space. So, progress on …