96 citations · 396 across the 27 of their papers we have counts for
24 papers · 1 filter
Replicable Dueling Bandits
Rohan Deb, Aadirupa Saha, Udaya Ghai +2
Dueling bandits choose each comparison based on earlier noisy outcomes, so two runs on the same preferences can compare different pairs. We study replicable dueling bandits, where…
Replicable Bandits with UCB based Exploration
Rohan Deb, Udaya Ghai, Karan Singh +1
We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration. A bandit algorithm is -replicable…
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…
Online Nonstochastic Model-Free Reinforcement Learning
Udaya Ghai, Arushi Gupta, Wenhan Xia +2
We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggl…
Variance-Reduced Conservative Policy Iteration
Naman Agarwal, Brian Bullins, Karan Singh
We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhi…
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…
Introduction to Online Control
Elad Hazan, Karan Singh
This text presents an introduction to an emerging paradigm in control of dynamical systems and differentiable reinforcement learning called online nonstochastic control. The new ap…
Machine Learning for Mechanical Ventilation Control (Extended Abstract)
Daniel Suo, Naman Agarwal, Wenhan Xia +12
Mechanical ventilation is one of the most widely used therapies in the ICU. However, despite broad application from anaesthesia to COVID-related life support, many injurious challe…
A Boosting Approach to Reinforcement Learning
Nataly Brukhim, Elad Hazan, Karan Singh
Reducing reinforcement learning to supervised learning is a well-studied and effective approach that leverages the benefits of compact function approximation to deal with large-sca…
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…
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…
Machine Learning for Mechanical Ventilation Control
Daniel Suo, Naman Agarwal, Wenhan Xia +12
We consider the problem of controlling an invasive mechanical ventilator for pressure-controlled ventilation: a controller must let air in and out of a sedated patient's lungs acco…
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…
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…
The Nonstochastic Control Problem
Elad Hazan, Sham M. Kakade, Karan Singh
We consider the problem of controlling an unknown linear dynamical system in the presence of (nonstochastic) adversarial perturbations and adversarial convex loss functions. In con…
Logarithmic Regret for Online Control
Naman Agarwal, Elad Hazan, Karan Singh
We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics. This…
Online Control with Adversarial Disturbances
Naman Agarwal, Brian Bullins, Elad Hazan +2
We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online c…
Provably Efficient Maximum Entropy Exploration
Elad Hazan, Sham M. Kakade, Karan Singh +1
Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studi…
Efficient Full-Matrix Adaptive Regularization
Naman Agarwal, Brian Bullins, Xinyi Chen +4
Adaptive regularization methods pre-multiply a descent direction by a preconditioning matrix. Due to the large number of parameters of machine learning problems, full-matrix precon…
Spectral Filtering for General Linear Dynamical Systems
Elad Hazan, Holden Lee, Karan Singh +2
We give a polynomial-time algorithm for learning latent-state linear dynamical systems without system identification, and without assumptions on the spectral radius of the system's…
Learning Linear Dynamical Systems via Spectral Filtering
Elad Hazan, Karan Singh, Cyril Zhang
We present an efficient and practical algorithm for the online prediction of discrete-time linear dynamical systems with a symmetric transition matrix. We circumvent the non-convex…
Efficient Regret Minimization in Non-Convex Games
Elad Hazan, Karan Singh, Cyril Zhang
We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural…
Dynamic Task Allocation for Crowdsourcing Settings
Angela Zhou, Irineo Cabreros, Karan Singh
We consider the problem of optimal budget allocation for crowdsourcing problems, allocating users to tasks to maximize our final confidence in the crowdsourced answers. Such an opt…
The Price of Differential Privacy For Online Learning
Naman Agarwal, Karan Singh
We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal regret boun…