Publications

Publications can also be found in my Google Scholar

S Ganesh and V Aggarwal. Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach. Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
Y Xu, S Ganesh, WU Mondal, Q Bai and V Aggarwal. Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm. Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
S Ganesh, J Chen, WU Mondal and V Aggarwal. Order-Optimal Global Convergence for Actor-Critic with General Policy and Neural Critic Parametrization. Uncertainty in Artificial Intelligence (UAI), 2025.
S Ganesh, WU Mondal and V Aggarwal. A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach. International Conference on Machine Learning (ICML), 2025.
S Ganesh, WU Mondal and V Aggarwal. Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite Horizon Average Reward MDPs. International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.
S Ganesh, A Reiffers-Masson and G Thoppe. Online Learning with Adversaries: A Differential Inclusion Analysis. Conference on Decision and Control (CDC), 2023.
S Ganesh, R Deb, G Thoppe and A Budhiraja. Does Momentum help? A Sample Complexity Analysis. Uncertainty in Artificial Intelligence (UAI), 2023.

S Ganesh, J Chen, G Thoppe and V Aggarwal. Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries. Transactions of Machine Learning Research (TMLR), November 2024.
S Ganesh and S Mohanty. Trees with Matrix Weights: Laplacian Matrix and Characteristic-like Vertices. Linear Algebra and its Applications, 646:195–237, 2022.

R Deb, S Ganesh and S Bhatnagar. Multi Timescale Stochastic Approximation: Stability and Convergence.
Y Xu, S Ganesh and V Aggarwal. Efficient Q-Learning and Actor-Critic Methods for Robust Average Reward Reinforcement Learning.