Sharan Vaswani

63 papers A* 10A 8Misc 1Journal 41Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes. CoRR Max Qiushi Lin, Reza Asad, Kevin Tan, Haque Ishfaq, Csaba Szepesvári, Sharan Vaswani
2026	J	`jnl`	Towards Parameter-Free Temporal Difference Learning. CoRR Yunxiang Li, Mark Schmidt, Reza Babanezhad, Sharan Vaswani
2025	J	`jnl`	(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum. Trans. Mach. Learn. Res. Anh Quang Dang, Reza Babanezhad Harikandeh, Sharan Vaswani
2025	A*	`conf`	Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster. ICML Sharan Vaswani, Reza Babanezhad Harikandeh
2025	J	`jnl`	Armijo Line-search Makes (Stochastic) Gradient Descent Go Fast. CoRR Sharan Vaswani, Reza Babanezhad
2025	A	`conf`	Fast Convergence of Softmax Policy Mirror Ascent. AISTATS Reza Asad, Reza Babanezhad Harikandeh, Issam H. Laradji, Nicolas Le Roux, Sharan Vaswani
2025	J	`jnl`	Glocal Smoothness: Line Search can really help! CoRR Curtis Fox, Aaron Mishkin, Sharan Vaswani, Mark Schmidt
2025	J	`jnl`	Preserving Plasticity in Continual Learning with Adaptive Linearity Injection. CoRR Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mo Chen, Sharan Vaswani
2025	J	`jnl`	Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation. CoRR Max Qiushi Lin, Jincheng Mei, Matin Aghaei, Michael Lu, Bo Dai, Alekh Agarwal, Dale Schuurmans, Csaba Szepesvári, Sharan Vaswani
2025	J	`jnl`	Revisiting Actor-Critic Methods in Discrete Action Off-Policy Reinforcement Learning. CoRR Reza Asad, Reza Babanezhad, Sharan Vaswani
2025	J	`jnl`	Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model. CoRR Xingtu Liu, Lin F. Yang, Sharan Vaswani
2025	J	`jnl`	Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates. CoRR Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani, Anant Raj, Csaba Szepesvári, Dale Schuurmans
2024	J	`jnl`	Fast Convergence of Softmax Policy Mirror Ascent. CoRR Reza Asad, Reza Babanezhad, Issam H. Laradji, Nicolas Le Roux, Sharan Vaswani
2024	A*	`conf`	From Inverse Optimization to Feasibility to ERM. ICML Saurabh Mishra, Anant Raj, Sharan Vaswani
2024	J	`jnl`	From Inverse Optimization to Feasibility to ERM. CoRR Saurabh Mishra, Anant Raj, Sharan Vaswani
2024	J	`jnl`	Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles. CoRR Shuman Peng, Arash Khoeini, Sharan Vaswani, Martin Ester
2024	J	`jnl`	Noise-adaptive (Accelerated) Stochastic Heavy-Ball Momentum. CoRR Anh Quang Dang, Reza Babanezhad, Sharan Vaswani
2024	A*	`conf`	Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates. NeurIPS Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani, Anant Raj, Csaba Szepesvári, Dale Schuurmans
2024	J	`jnl`	Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs. RLJ Michael Lu, Matin Aghaei, Anant Raj, Sharan Vaswani
2024	J	`jnl`	Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs. CoRR Michael Lu, Matin Aghaei, Anant Raj, Sharan Vaswani
2023	A*	`conf`	Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees. NeurIPS Sharan Vaswani, Amirreza Kazemi, Reza Babanezhad Harikandeh, Nicolas Le Roux
2023	J	`jnl`	Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees. CoRR Sharan Vaswani, Amirreza Kazemi, Reza Babanezhad, Nicolas Le Roux
2023	A*	`conf`	Target-based Surrogates for Stochastic Optimization. ICML Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad Harikandeh, Mark Schmidt, Nicolas Le Roux
2023	J	`jnl`	Target-based Surrogates for Stochastic Optimization. CoRR Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Nicolas Le Roux
2022	A	`conf`	A general class of surrogate functions for stable and efficient reinforcement learning. AISTATS Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Müller, Shivam Garg, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux
2022	—	`conf`	Improved Policy Optimization for Online Imitation Learning. CoLLAs Jonathan Wilder Lavington, Sharan Vaswani, Mark Schmidt
2022	J	`jnl`	Improved Policy Optimization for Online Imitation Learning. CoRR Jonathan Wilder Lavington, Sharan Vaswani, Mark Schmidt
2022	A*	`conf`	Near-Optimal Sample Complexity Bounds for Constrained MDPs. NeurIPS Sharan Vaswani, Lin Yang, Csaba Szepesvári
2022	J	`jnl`	Near-Optimal Sample Complexity Bounds for Constrained MDPs. CoRR Sharan Vaswani, Lin F. Yang, Csaba Szepesvári
2022	J	`jnl`	SVRG meets AdaGrad: painless variance reduction. Mach. Learn. Benjamin Dubois-Taine, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Simon Lacoste-Julien
2022	A*	`conf`	Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent. ICML Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad
2022	J	`jnl`	Towards Painless Policy Optimization for Constrained MDPs. CoRR Arushi Jain, Sharan Vaswani, Reza Babanezhad, Csaba Szepesvári, Doina Precup
2022	A	`conf`	Towards painless policy optimization for constrained MDPs. UAI Arushi Jain, Sharan Vaswani, Reza Babanezhad, Csaba Szepesváari, Doina Precup
2021	J	`jnl`	A functional mirror ascent view of policy gradient methods with function approximation. CoRR Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Mueller, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux
2021	J	`jnl`	SVRG Meets AdaGrad: Painless Variance Reduction. CoRR Benjamin Dubois-Taine, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Simon Lacoste-Julien
2021	A	`conf`	Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence. AISTATS Nicolas Loizou, Sharan Vaswani, Issam Hadj Laradji, Simon Lacoste-Julien
2021	J	`jnl`	Towards Noise-adaptive, Problem-adaptive Stochastic Gradient Descent. CoRR Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad
2020	J	`jnl`	Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search). CoRR Sharan Vaswani, Frederik Kunstner, Issam H. Laradji, Si Yi Meng, Mark Schmidt, Simon Lacoste-Julien
2020	J	`jnl`	Combining Bayesian optimization and Lipschitz optimization. Mach. Learn. Mohamed Osama Ahmed, Sharan Vaswani, Mark Schmidt
2020	A	`conf`	Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation. AISTATS Si Yi Meng, Sharan Vaswani, Issam Hadj Laradji, Mark Schmidt, Simon Lacoste-Julien
2020	A	`conf`	Old Dog Learns New Tricks: Randomized UCB for Bandit Problems. AISTATS Sharan Vaswani, Abbas Mehrabian, Audrey Durand, Branislav Kveton
2020	J	`jnl`	Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence. CoRR Nicolas Loizou, Sharan Vaswani, Issam H. Laradji, Simon Lacoste-Julien
2020	J	`jnl`	To Each Optimizer a Norm, To Each Norm its Generalization. CoRR Sharan Vaswani, Reza Babanezhad, Jose Gallego, Aaron Mishkin, Simon Lacoste-Julien, Nicolas Le Roux
2019	A	`conf`	Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron. AISTATS Sharan Vaswani, Francis R. Bach, Mark Schmidt
2019	J	`jnl`	Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation. CoRR Si Yi Meng, Sharan Vaswani, Issam H. Laradji, Mark Schmidt, Simon Lacoste-Julien
2019	A*	`conf`	Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits. ICML Branislav Kveton, Csaba Szepesvári, Sharan Vaswani, Zheng Wen, Tor Lattimore, Mohammad Ghavamzadeh
2019	J	`jnl`	Old Dog Learns New Tricks: Randomized UCB for Bandit Problems. CoRR Sharan Vaswani, Abbas Mehrabian, Audrey Durand, Branislav Kveton
2019	A*	`conf`	Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates. NeurIPS Sharan Vaswani, Aaron Mishkin, Issam H. Laradji, Mark Schmidt, Gauthier Gidel, Simon Lacoste-Julien
2019	J	`jnl`	Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates. CoRR Sharan Vaswani, Aaron Mishkin, Issam H. Laradji, Mark Schmidt, Gauthier Gidel, Simon Lacoste-Julien
2018	J	`jnl`	Combining Bayesian Optimization and Lipschitz Optimization. CoRR Mohamed Osama Ahmed, Sharan Vaswani, Mark Schmidt
2018	J	`jnl`	Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron. CoRR Sharan Vaswani, Francis R. Bach, Mark Schmidt
2018	J	`jnl`	New Insights into Bootstrapping for Bandits. CoRR Sharan Vaswani, Branislav Kveton, Zheng Wen, Anup Rao, Mark Schmidt, Yasin Abbasi-Yadkori
2017	J	`jnl`	Diffusion Independent Semi-Bandit Influence Maximization. CoRR Sharan Vaswani, Branislav Kveton, Zheng Wen, Mohammad Ghavamzadeh, Laks V. S. Lakshmanan, Mark Schmidt
2017	A	`conf`	Horde of Bandits using Gaussian Markov Random Fields. AISTATS Sharan Vaswani, Mark Schmidt, Laks V. S. Lakshmanan
2017	J	`jnl`	Horde of Bandits using Gaussian Markov Random Fields. CoRR Sharan Vaswani, Mark Schmidt, Laks V. S. Lakshmanan
2017	A*	`conf`	Model-Independent Online Learning for Influence Maximization. ICML Sharan Vaswani, Branislav Kveton, Zheng Wen, Mohammad Ghavamzadeh, Laks V. S. Lakshmanan, Mark Schmidt
2017	—	`conf`	Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback. NIPS Zheng Wen, Branislav Kveton, Michal Valko, Sharan Vaswani
2016	J	`jnl`	Adaptive Influence Maximization in Social Networks: Why Commit when You can Adapt? CoRR Sharan Vaswani, Laks V. S. Lakshmanan
2015	J	`jnl`	Influence Maximization with Bandits. CoRR Sharan Vaswani, Laks V. S. Lakshmanan
2014	J	`jnl`	Modeling Non-Progressive Phenomena for Influence Propagation. CoRR Vincent Yun Lou, Smriti Bhagat, Laks V. S. Lakshmanan, Sharan Vaswani
2014	—	`conf`	Modeling non-progressive phenomena for influence propagation. COSN Vincent Yun Lou, Smriti Bhagat, Laks V. S. Lakshmanan, Sharan Vaswani
2013	J	`jnl`	Fast 3D Salient Region Detection in Medical Images using GPUs. CoRR Rahul Thota, Sharan Vaswani, Amit A. Kale, Nagavijayalakshmi Vydyanathan
2013	Misc	`conf`	Performance evaluation of medical imaging algorithms on Intel HiPC Jyotsna Khemka, Mrugesh R. Gajjar, Sharan Vaswani, Naga Vydyanathan, Rama Malladi, Vinutha S. V