
Linear Convergence of EntropyRegularized Natural Policy Gradient with Linear Function Approximation
Natural policy gradient (NPG) methods with function approximation achiev...
read it

The Dynamics of Gradient Descent for Overparametrized Neural Networks
We consider the dynamics of gradient descent (GD) in overparameterized s...
read it

Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
We propose two algorithms for episodic stochastic shortest path problems...
read it

Achieving Small Test Error in Mildly Overparameterized Neural Networks
Recent theoretical works on overparameterized neural nets have focused ...
read it

Sample Complexity and Overparameterization Bounds for ProjectionFree Neural TD Learning
We study the dynamics of temporaldifference learning with neural networ...
read it

Optimistic Policy Iteration for MDPs with Acyclic Transient State Structure
We consider Markov Decision Processes (MDPs) in which every stationary p...
read it

Onebit feedback is sufficient for upper confidence bound policies
We consider a variant of the traditional multiarmed bandit problem in w...
read it

Combining Reinforcement Learning with Model Predictive Control for OnRamp Merging
We consider the problem of designing an algorithm to allow a car to auto...
read it

On the Consistency of Maximum Likelihood Estimators for Causal Network Identification
We consider the problem of identifying parameters of a particular class ...
read it

Hellinger KLUCB based Bandit Algorithms for Markovian and i.i.d. Settings
In the regretbased formulation of multiarmed bandit (MAB) problems, ex...
read it

Optimal Load Balancing in Bipartite Graphs
Applications in cloud platforms motivate the study of efficient load bal...
read it

ProvablyEfficient Double QLearning
In this paper, we establish a theoretical comparison between the asympto...
read it

Robust MultiAgent MultiArmed Bandits
There has been recent interest in collaborative multiagent bandits, whe...
read it

The Global Landscape of Neural Networks: An Overview
One of the major concerns for neural network training is that the nonco...
read it

ContinuousTime MultiArmed Bandits with Controlled Restarts
Timeconstrained decision processes have been ubiquitous in many fundame...
read it

BudgetConstrained Bandits over General Cost and Reward Distributions
We consider a budgetconstrained bandit problem where each arm pull incu...
read it

Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity
Traditional landscape analysis of deep neural networks aims to show that...
read it

Optimal Search Segmentation Mechanisms for Online Platform Markets
Online platforms, such as Airbnb, hotels.com, Amazon, Uber and Lyft, can...
read it

FiniteTime Performance Bounds and Adaptive Learning Rate Selection for Two TimeScale Reinforcement Learning
We study two timescale linear stochastic approximation algorithms, whic...
read it

FiniteTime Error Bounds For Linear Stochastic Approximation and TD Learning
We consider the dynamics of a linear stochastic approximation algorithm ...
read it

Almost Boltzmann Exploration
Boltzmann exploration is widely used in reinforcement learning to provid...
read it

HeavyTraffic Insensitive Bounds for Weighted Proportionally Fair Bandwidth Sharing Policies
We consider a connectionlevel model proposed by Massoulié and Roberts f...
read it

Adding One Neuron Can Eliminate All Bad Local Minima
One of the main difficulties in analyzing neural networks is the noncon...
read it

Learning Latent Events from Network Message Logs: A Decomposition Based Approach
In this communication, we describe a novel technique for event mining us...
read it

Understanding the Loss Surface of Neural Networks for Binary Classification
It is widely conjectured that the reason that training algorithms for ne...
read it

Delay Asymptotics and Bounds for MultiTask Parallel Jobs
We study delay of jobs that consist of multiple parallel tasks, which is...
read it

Asymptotic response time analysis for multitask parallel jobs
The response time of jobs with multiple parallel tasks is a critical per...
read it

Enhancing The Reliability of Outofdistribution Image Detection in Neural Networks
We consider the problem of detecting outofdistribution images in neura...
read it

Optimal HeavyTraffic Queue Length Scaling in an Incompletely Saturated Switch
We consider an input queued switch operating under the MaxWeight schedul...
read it

Why Deep Neural Networks for Function Approximation?
Recently there has been much interest in understanding why deep neural n...
read it

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits
We study contextual bandits with budget and time constraints, referred t...
read it

Clustering and Inference From Pairwise Comparisons
Given a set of pairwise comparisons, the classical ranking problem compu...
read it

Collaborative Filtering with InformationRich and InformationSparse Entities
In this paper, we consider a popular model for collaborative filtering i...
read it

Jointly Clustering Rows and Columns of Binary Matrices: Algorithms and Tradeoffs
In standard clustering problems, data points are represented by vectors,...
read it

Learning Loosely Connected Markov Random Fields
We consider the structure learning problem for graphical models that we ...
read it
R. Srikant
is this you? claim profile
Fredric G. and Elizabeth H. Endowed Professor Department of Electrical and Computer Engineering, Professor, Coordinated Science Lab at University of Illinois at UrbanaChampaign