As large language models increase in capability, researchers have starte...
We consider a collaborative learning setting where each agent's goal is ...
Regulators and academics are increasingly interested in the causal effec...
We initiate a principled study of algorithmic collective action on digit...
We introduce the notion of performative power, which measures the abilit...
In performative prediction, the deployment of a predictive model trigger...
When reasoning about strategic behavior in a machine learning context it...
An increasingly common setting in machine learning involves multiple par...
Proximal Policy Optimization (PPO) is a popular deep policy gradient
alg...
We study preconditioned gradient-based optimization methods where the
pr...
In this paper we tackle the challenge of making the stochastic coordinat...
In performative prediction, the choice of a model influences the distrib...
When predictions support decisions they may influence the outcome they a...
In this paper we propose a novel parallel stochastic coordinate descent ...
In this paper we analyze, evaluate, and improve the performance of train...
Distributed machine learning training is one of the most common and impo...
This paper presents Acquisition Thompson Sampling (ATS), a novel algorit...