activity
20172026
most citedProvably Efficient Maximum Entropy Exploration

96 citations · 135 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2025

Sample-Optimal Agnostic Boosting with Unlabeled Data

Udaya Ghai, Karan Singh

Boosting provides a practical and provably effective framework for constructing accurate learning algorithms from inaccurate rules of thumb. It extends the promise of sample-effici…

cs.LG2022

Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret

Gautam Goel, Naman Agarwal, Karan Singh +1

We consider the fundamental problem of online control of a linear dynamical system from two different viewpoints: regret minimization and competitive analysis. We prove that the op…

cs.LG20213 cited

A Regret Minimization Approach to Iterative Learning Control

Naman Agarwal, Elad Hazan, Anirudha Majumdar +1

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new perform…

cs.LG20211 cited

Boosting for Online Convex Optimization

Elad Hazan, Karan Singh

We consider the decision-making framework of online convex optimization with a very large number of experts. This setting is ubiquitous in contextual and reinforcement learning pro…

cs.LG2020

No-Regret Prediction in Marginally Stable Systems

Udaya Ghai, Holden Lee, Karan Singh +2

We consider the problem of online prediction in a marginally stable linear dynamical system subject to bounded adversarial or (non-isotropic) stochastic perturbations. This poses t…

cs.LG2020

Improper Learning for Non-Stochastic Control

Max Simchowitz, Karan Singh, Elad Hazan

We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed…