← Authors

Sharan Vaswani

19 papers · 2017–2025 · 4 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (25) 🧭 Keyword Pioneer πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (8) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10) πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (75) πŸ’Ž Century Club (19) πŸ”₯ Unstoppable (7) πŸ“ˆ Trend Setter

Conferences

AISTATS (7) ICML (6) NIPS (5) UAI (1)

Top co-authors

Mark Schmidt (6) Csaba SzepesvΓ‘ri (4) Reza Babanezhad Harikandeh (4) Branislav Kveton (4) Nicolas Le Roux (4) Simon Lacoste-Julien (3) Zheng Wen (3) Mohammad Ghavamzadeh (2) Reza Babanezhad (2) Anant Raj (2)

Keywords

stochastic gradient descent (5) multi-armed bandit (4) policy optimization (3) online learning (3) regret bound (3) convergence rate (3) thompson sampling (2) over-parameterized model (2) surrogate function (2) social network (2) bandit algorithm (2) learning rate (2) influence maximization (2) exploration-exploitation tradeoff (2) contextual bandit (2) nesterov acceleration (2) regret minimization (1) imitation learning (1) perceptron algorithm (1) sample complexity (1)

Papers

Fast Convergence of Softmax Policy Mirror Ascent AISTATS 2025
Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster ICML 2025
From Inverse Optimization to Feasibility to ERM ICML 2024
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates NIPS 2024
Target-based Surrogates for Stochastic Optimization ICML 2023
Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees NIPS 2023
Towards painless policy optimization for constrained MDPs UAI 2022
A general class of surrogate functions for stable and efficient reinforcement learning AISTATS 2022
Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent ICML 2022
Near-Optimal Sample Complexity Bounds for Constrained MDPs NIPS 2022
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence AISTATS 2021
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation AISTATS 2020
Old Dog Learns New Tricks: Randomized UCB for Bandit Problems AISTATS 2020
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates NIPS 2019
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits ICML 2019
Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron AISTATS 2019
Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback NIPS 2017
Horde of Bandits using Gaussian Markov Random Fields AISTATS 2017
Model-Independent Online Learning for Influence Maximization ICML 2017