Gugan Thoppe

According to our database, Gugan Thoppe authored at least 22 papers between 2012 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries.

Swetha Ganesh, Jiayu Chen, Gugan Thoppe, Vaneet Aggarwal

CoRR, 2024

2023

VaR\ and CVaR Estimation in a Markov Cost Process: Lower and Upper Bounds.

Sanjay Bhat, Prashanth L. A., Gugan Thoppe

CoRR, 2023

SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search.

Gal Dalal, Assaf Hallak, Gugan Thoppe, Shie Mannor, Gal Chechik

CoRR, 2023

Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking.

Eshwar S. R, Shishir Kolathaya, Gugan Thoppe

Proceedings of the Performance Evaluation Methodologies and Tools, 2023

Does Momentum Help in Stochastic Optimization? A Sample Complexity Analysis.

Swetha Ganesh, Rohan Deb, Gugan Thoppe, Amarjit Budhiraja

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Online Learning with Adversaries: A Differential-Inclusion Analysis.

Swetha Ganesh, Alexandre Reiffers-Masson, Gugan Thoppe

Proceedings of the 62nd IEEE Conference on Decision and Control, 2023

2022

Online algorithms for estimating change rates of web pages.

Konstantin Avrachenkov, Kishor Patil, Gugan Thoppe

Perform. Evaluation, 2022

Approximate Q-learning and SARSA(0) under the ε-greedy Policy: a Differential Inclusion Analysis.

Aditya Gopalan, Gugan Thoppe

CoRR, 2022

2021

Does Momentum Help? A Sample Complexity Analysis.

Gugan Thoppe, Rohan Deb, Swetha Ganesh, Amarjit Budhiraja

CoRR, 2021

Scale Invariant Solutions for Overdetermined Linear Systems with Applications to Reinforcement Learning.

Rahul Madhavan, Gugan Thoppe, Hemanta Makwana

CoRR, 2021

A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning.

Gugan Thoppe, Bhumesh Kumar

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Randomly Weighted d-Complexes: Minimal Spanning Acycles and Persistence Diagrams.

Primoz Skraba, Gugan Thoppe, D. Yogeshwaran

Electron. J. Comb., 2020

Change Rate Estimation and Optimal Freshness in Web Page Crawling.

Konstantin Avrachenkov, Kishor Patil, Gugan Thoppe

Proceedings of the VALUETOOLS 2020: 13th EAI International Conference on Performance Evaluation Methodologies and Tools, 2020

A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound.

Gal Dalal, Balázs Szörényi, Gugan Thoppe

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2018

Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning.

Gal Dalal, Gugan Thoppe, Balázs Szörényi, Shie Mannor

Proceedings of the Conference On Learning Theory, 2018

Finite Sample Analyses for TD(0) With Function Approximation.

Gal Dalal, Balázs Szörényi, Gugan Thoppe, Shie Mannor

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017

Finite Sample Analysis for TD(0) with Linear Function Approximation.

Gal Dalal, Balázs Szörényi, Gugan Thoppe, Shie Mannor

CoRR, 2017

Concentration Bounds for Two Timescale Stochastic Approximation with Applications to Reinforcement Learning.

Gal Dalal, Balázs Szörényi, Gugan Thoppe, Shie Mannor

CoRR, 2017

2016

A concentration result for stochastic approximation (Extended abstract).

Gugan Thoppe, Vivek S. Borkar

Proceedings of the 2016 Information Theory and Applications Workshop, 2016

2014

An Improved Block Coordinate Descent Method for Quadratic Programming in High Dimensions.

Gugan Thoppe, Vivek S. Borkar, Dinesh Garg

CoRR, 2014

A stochastic Kaczmarz algorithm for network tomography.

Gugan Thoppe, Vivek S. Borkar, D. Manjunath

Autom., 2014

2012

Generalized network tomography.

Gugan Thoppe

Proceedings of the 50th Annual Allerton Conference on Communication, 2012