Gugan Thoppe | गुगन थोप्पे
Gugan Thoppe | गुगन थोप्पे
Other namesGugan Thoppe, Gugan Chandrashekar Thoppe
Asst. Prof., Computer Science, Indian Institute of Science | भारतीय विज्ञान संस्थान
Verified email at - Homepage
Cited by
Cited by
Finite Sample Analyses for TD (0) with Function Approximation
G Dalal, B Szörényi, G Thoppe, S Mannor
AAAI Conference on Artificial Intelligence 32, 6144-6160, 2018
Finite Sample Analysis of Two-timescale Stochastic Approximation with Applications to Reinforcement Learning
G Dalal, B Szörényi, G Thoppe, S Mannor
Conference On Learning Theory 31, 1199-1233, 2018
A Concentration Bound for Stochastic Approximation via Alekseev’s Formula
G Thoppe, V Borkar
Stochastic Systems 9 (1), 1-26, 2019
A Tale of Two-timescale Reinforcement Learning with the Tightest Finite-time Bound
G Dalal, B Szorenyi, G Thoppe
AAAI Conference on Artificial Intelligence 34 (04), 3701-3708, 2020
Randomly Weighted complexes: Minimal Spanning Acycles and Persistence Diagrams
P Skraba, G Thoppe, D Yogeshwaran
Electronic Journal of Combinatorics 27 (2), 1-47, 2020
A stochastic Kaczmarz algorithm for network tomography
G Thoppe, V Borkar, D Manjunath
Automatica 50 (3), 910-914, 2014
Online Algorithms for Estimating Change Rates of Web Pages
K Avrachenkov, K Patil, G Thoppe
Performance Evaluation 153, 1-21, 2022
Limit theorems for topological invariants of the dynamic multi-parameter simplicial complex
T Owada, G Samorodnitsky, G Thoppe
Stochastic Processes and their Applications 138, 56-95, 2021
On the Evolution of Topology in Dynamic Clique Complexes
G Thoppe, D Yogeshwaran, R Adler
Advances in Applied Probability 48 (4), 989-1014, 2016
Change rate estimation and optimal freshness in Web page crawling
K Avrachenkov, K Patil, G Thoppe
EAI Valuetools Conference on Performance Evaluation Methodologies and Tools …, 2020
Greedy block coordinate descent (GBCD) method for high dimensional quadratic programs
G Thoppe, VS Borkar, D Garg
arXiv preprint arXiv:1404.6635, 2014
Betti numbers of Gaussian excursions in the sparse regime
G Thoppe, SR Krishnan
arXiv preprint arXiv:1807.11018, 2018
Demystifying Approximate Value-based RL with ε-greedy Exploration: A Differential Inclusion View
A Gopalan, G Thoppe
arXiv preprint arXiv:2205.13617, 2024
Does Momentum Help in Stochastic Optimization? A Sample Complexity Analysis
S Ganesh, R Deb, G Thoppe, A Budhiraja
Uncertainty in Artificial Intelligence (UAI) 39, 2023
The Shadow Knows: Empirical Distributions of Minimal Spanning Acycles and Persistence Diagrams of Random Complexes
N Fraiman, S Mukherjee, G Thoppe
Discrete Analysis, 2023
A Law of Iterated Logarithm for Multi-agent Reinforcement Learning
G Thoppe, B Kumar
Advances in Neural Information Processing Systems (Neurips) 34, 2021
Generalized network tomography
G Thoppe
Allerton Conference on Communication, Control, and Computing 50, 762-769, 2012
Online Learning with Adversaries: A Differential Inclusion Analysis
S Ganesh, A Reiffers-Masson, G Thoppe
Conference on Decision and Control (CDC) 62, 2023
SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search
G Dalal, A Hallak, G Thoppe, S Mannor, G Chechik
arXiv preprint arXiv:2301.13236, 2024
Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
S Ganesh, J Chen, G Thoppe, V Aggarwal
arXiv preprint arXiv:2403.09940, 2024
The system can't perform the operation now. Try again later.
Articles 1–20