Ashok Cutkosky

General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization ICML 2025 Descent with Misaligned Gradients and Applications to Hidden Convexity ICLR 2025 Unconstrained Robust Online Convex Optimization ICML 2025 Private Zeroth-Order Nonsmooth Nonconvex Optimization ICLR 2024 Improving Adaptive Online Learning Using Refined Discretization ALT 2024 Adam with model exponential moving average is effective for nonconvex optimization NIPS 2024 The Road Less Scheduled NIPS 2024 Fully Unconstrained Online Learning NIPS 2024 Random Scaling and Momentum for Non-smooth Non-convex Optimization ICML 2024 Online Linear Regression in Dynamic Environments via Discounting ICML 2024 Bandit Online Linear Optimization with Hints and Queries ICML 2023 Alternation makes the adversary weaker in two-player games NIPS 2023 Mechanic: A Learning Rate Tuner NIPS 2023 Unconstrained Dynamic Regret via Sparse Coding NIPS 2023 Long Range Language Modeling via Gated State Spaces ICLR 2023 Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion ICML 2023 Unconstrained Online Learning with Unbounded Losses ICML 2023 Parameter-free Regret in High Probability with Heavy Tails NIPS 2022 Momentum Aggregation for Private Non-convex ERM NIPS 2022 Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory AISTATS 2022 Implicit Parameter-free Online Learning with Truncated Linear Models ALT 2022 Leveraging Initial Hints for Free in Stochastic Linear Bandits ALT 2022 Differentially Private Online-to-batch for Smooth Losses NIPS 2022 Parameter-free Mirror Descent COLT 2022 PDE-Based Optimal Strategy for Unconstrained Online Learning ICML 2022 Optimal Comparator Adaptive Online Learning with Switching Cost NIPS 2022 Better SGD using Second-order Momentum NIPS 2022 Robust Pure Exploration in Linear Bandits with Limited Budget ICML 2021 Power of Hints for Online Learning with Movement Costs AISTATS 2021 Logarithmic Regret from Sublinear Hints NIPS 2021 High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails NIPS 2021 Dynamic Balancing for Model Selection in Bandits and RL ICML 2021 Extreme Memorization via Scale of Initialization ICLR 2021 Online Selective Classification with Limited Feedback NIPS 2021 Comparator-Adaptive Convex Bandits NIPS 2020 Online Linear Optimization with Many Hints NIPS 2020 Better Full-Matrix Regret via Parameter-Free Online Learning NIPS 2020 Online Learning with Imperfect Hints ICML 2020 Parameter-free, Dynamic, and Strongly-Adaptive Online Learning ICML 2020 Momentum Improves Normalized SGD ICML 2020 Momentum-Based Variance Reduction in Non-Convex SGD NIPS 2019 Combining Online Learning Guarantees COLT 2019 Artificial Constraints and Hints for Unbounded Online Learning COLT 2019 Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration NIPS 2019 Matrix-Free Preconditioning in Online Learning ICML 2019 Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization ICML 2019 Anytime Online-to-Batch, Optimism and Acceleration ICML 2019 Distributed Stochastic Optimization via Adaptive SGD NIPS 2018 Black-Box Reductions for Parameter-free Online Learning in Banach Spaces COLT 2018 Online Learning Without Prior Information COLT 2017 Stochastic and Adversarial Online Learning without Hyperparameters NIPS 2017 Online Convex Optimization with Unconstrained Domains and Losses NIPS 2016