
TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search
Molecular geometry prediction of flexible molecules, or conformer search...
read it

LowRank Generalized Linear Bandit Problems
In a lowrank linear bandit problem, the reward of an action (represente...
read it

On the Equivalence between Online and Private Learnability beyond Binary Classification
Alon et al. [2019] and Bun et al. [2020] recently showed that online lea...
read it

On Learnability under General Stochastic Processes
Statistical learning theory under independent and identically distribute...
read it

Nearoptimal Reinforcement Learning in Factored MDPs: OracleEfficient Algorithms for the Nonepisodic Setting
We study reinforcement learning in factored Markov decision processes (F...
read it

Nearoptimal Oracleefficient Algorithms for Stationary and NonStationary Stochastic Linear Bandits
We investigate the design of two algorithms that enjoy not only computat...
read it

Online Boosting for Multilabel Ranking with Topk Feedback
We present online boosting algorithms for multilabel ranking with topk ...
read it

Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles
Reinforcement learning (RL) methods have been shown to be capable of lea...
read it

Thompson Sampling in NonEpisodic Restless Bandits
Restless bandit problems assume timevarying reward distributions of the...
read it

What You See May Not Be What You Get: UCB Bandit Algorithms Robust to εContamination
Motivated by applications of bandit algorithms in education, we consider...
read it

Not All are Made Equal: Consistency of Weighted Averaging Estimators Under Active Learning
Active learning seeks to build the best possible model with a budget of ...
read it

Regret Analysis of Causal Bandit Problems
We study how to learn optimal interventions sequentially given causal in...
read it

Regret Bounds for Thompson Sampling in Restless Bandit Problems
Restless bandit problems are instances of nonstationary multiarmed ban...
read it

Generalization Bounds in the PredictthenOptimize Framework
The predictthenoptimize framework is fundamental in many practical set...
read it

Randomized Algorithms for DataDriven Stabilization of Stochastic Linear Systems
Datadriven control strategies for dynamical systems with unknown parame...
read it

Contextual Markov Decision Processes using Generalized Linear Models
We consider the recently proposed reinforcement learning (RL) framework ...
read it

On Applications of Bootstrap in Continuous Space Reinforcement Learning
In decision making problems for continuous state and action spaces, line...
read it

On the Optimality of Perturbations in Stochastic and Adversarial Multiarmed Bandit Problems
We investigate the optimality of perturbation based algorithms in the st...
read it

Input Perturbations for Adaptive Regulation and Learning
Design of adaptive algorithms for simultaneous regulation and estimation...
read it

Online Multiclass Boosting with Bandit Feedback
We present online boosting algorithms for multiclass classification with...
read it

Fighting Contextual Bandits with Stochastic Smoothing
We introduce a new stochastic smoothing perspective to study adversarial...
read it

Random ReLU Features: Universality, Approximation, and Composition
We propose random ReLU features models in this work. Its motivation is r...
read it

But How Does It Work in Theory? Linear SVM with Random Features
We prove that, under low noise assumptions, the support vector machine w...
read it

Finite Time Adaptive Stabilization of LQ Systems
Stabilization of linear systems with unknown dynamics is a canonical pro...
read it

On Optimality of Adaptive LinearQuadratic Regulators
Adaptive regulation of linear systems represents a canonical problem in ...
read it

Finite Time Analysis of Optimal Adaptive Policies for LinearQuadratic Systems
We consider the classical problem of control of linear systems with quad...
read it

Markov Decision Processes with Continuous Side Information
We consider a reinforcement learning (RL) setting in which the agent int...
read it

Action Centered Contextual Bandits
Contextual bandits have become popular as they offer a middle ground bet...
read it

Online Boosting Algorithms for Multilabel Ranking
We consider the multilabel ranking approach to multilabel learning. Bo...
read it

An ActorCritic Contextual Bandit Algorithm for Personalized Mobile Health Interventions
Increasing technological sophistication and widespread use of smartphone...
read it

Online Multiclass Boosting
Recent work has extended the theoretical analysis of boosting algorithms...
read it

Beyond the Hazard Rate: More Perturbation Algorithms for Adversarial Multiarmed Bandits
Recent work on follow the perturbed leader (FTPL) algorithms for the adv...
read it

Sampled Fictitious Play is Hannan Consistent
Fictitious play is a simple and widely studied adaptive heuristic for pl...
read it

Mixture Proportion Estimation via Kernel Embedding of Distributions
Mixture proportion estimation (MPE) is the problem of estimating the wei...
read it

Lasso Guarantees for Time Series Estimation Under Subgaussian Tails and βMixing
Many theoretical results on estimation of high dimensional time series r...
read it

Fighting Bandits with a New Kind of Smoothness
We define a novel family of algorithms for the adversarial multiarmed b...
read it

Handling Class Imbalance in Link Prediction using Learning to Rank Techniques
We consider the link prediction problem in a partially observed network,...
read it

Perceptron like Algorithms for Online Learning to Rank
Perceptron is a classic online algorithm for learning a classification f...
read it

Consistent Algorithms for Multiclass Classification with a Reject Option
We consider the problem of nclass classification (n≥ 2), where the clas...
read it

On Iterative Hard Thresholding Methods for Highdimensional MEstimation
The use of Mestimators in generalized linear regression models in high ...
read it

Perceptronlike Algorithms and Generalization Bounds for Learning to Rank
Learning to rank is a supervised learning problem where the output space...
read it

On Lipschitz Continuity and Smoothness of Loss Functions in Learning to Rank
In binary classification and regression problems, it is well understood ...
read it

Feature Clustering for Accelerating Parallel Coordinate Descent
Largescale L1regularized loss minimization problems arise in highdime...
read it

The Interplay Between Stability and Regret in Online Learning
This paper considers the stability of online learning algorithms and its...
read it

Scaling Up Coordinate Descent Algorithms for Large ℓ_1 Regularization Problems
We present a generic framework for parallel coordinate descent (CD) algo...
read it

Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
Online learning algorithms are designed to learn even when their input i...
read it

Orthogonal Matching Pursuit with Replacement
In this paper, we consider the problem of compressed sensing where the g...
read it

Online Learning: Stochastic and Constrained Adversaries
Learning theory has largely focused on two main learning scenarios. The ...
read it

Online Learning: Beyond Regret
We study online learnability of a wide class of problems, extending the ...
read it

Learning Exponential Families in HighDimensions: Strong Convexity and Sparsity
The versatility of exponential families, along with their attendant conv...
read it
Ambuj Tewari
is this you? claim profile
Associate Professor of Statistics, Associate Professor of Electrical Engineering and Computer Science