Sharan Vaswani

Publications

Fast Convergence of Softmax Policy Mirror Ascent. Reza Asad, Reza Babanezhad, Issam H. Laradji, Nicolas Le Roux, Sharan Vaswani. At International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.

Fast Convergence of Softmax Policy Mirror Ascent for Bandits & Tabular MDPs. Issam H. Laradji, Reza Asad, Sharan Vaswani. At Workshop at the Neural Information Processing Systems (NeurIPS), 2024.

Surrogate Minimization: An Optimization Algorithm for Training Large Neural Networks with Model Parallelism. Reza Asad, Reza Babanezhad, Issam H. Laradji, Nicolas Le Roux, Sharan Vaswani. At Workshop at the Neural Information Processing Systems (NeurIPS), 2023.

Stochastic polyak step-size for sgd: An adaptive learning rate for fast convergence. Nicolas Loizou, Sharan Vaswani, Issam H. Laradji, Simon Lcoste-Julien. At International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.

Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation. Si Yi Meng, Sharan Vaswani, Issam H. Laradji, Mark Schmidt, Simon Lcoste-Julien. At International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.

PDF Cite Slides Video

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates. Sharan Vaswani, Aaron Mishkin, Issam H. Laradji, Mark Schmidt, Gauthier Gidel, Simon Lcoste-Julien. At Conference on Neural Information Processing Systems (NeurIPS), 2019.