| 2026 | COLT | Adaptive Weighted Averaging. | Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit |
| 2025 | ICLR | Descent with Misaligned Gradients and Applications to Hidden Convexity. | Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit |
| 2025 | ICML | General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization. | Kwangjun Ahn, Gagik Magakyan, Ashok Cutkosky |
| 2025 | ICML | Unconstrained Robust Online Convex Optimization. | Jiujia Zhang, Ashok Cutkosky |
| 2024 | ALT | Improving Adaptive Online Learning Using Refined Discretization. | Zhiyu Zhang, Heng Yang, Ashok Cutkosky, Ioannis Ch. Paschalidis |
| 2024 | ICLR | Private Zeroth-Order Nonsmooth Nonconvex Optimization. | Qinzi Zhang, Hoang Tran, Ashok Cutkosky |
| 2024 | ICML | Online Linear Regression in Dynamic Environments via Discounting. | Andrew Jacobsen, Ashok Cutkosky |
| 2024 | ICML | Random Scaling and Momentum for Non-smooth Non-convex Optimization. | Qinzi Zhang, Ashok Cutkosky |
| 2023 | ICLR | Long Range Language Modeling via Gated State Spaces. | Harsh Mehta, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur |
| 2023 | ICML | Bandit Online Linear Optimization with Hints and Queries. | Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit |
| 2023 | ICML | Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. | Ashok Cutkosky, Harsh Mehta, Francesco Orabona |
| 2023 | ICML | Unconstrained Online Learning with Unbounded Losses. | Andrew Jacobsen, Ashok Cutkosky |
| 2023 | UAI | Blackbox optimization of unimodal functions. | Ashok Cutkosky, Abhimanyu Das, Weihao Kong, Chansoo Lee, Rajat Sen |
| 2022 | AISTATS | Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory. | Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis |
| 2022 | ALT | Implicit Parameter-free Online Learning with Truncated Linear Models. | Keyi Chen, Ashok Cutkosky, Francesco Orabona |
| 2022 | ALT | Leveraging Initial Hints for Free in Stochastic Linear Bandits. | Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Qiuyi (Richard) Zhang |
| 2022 | COLT | Parameter-free Mirror Descent. | Andrew Jacobsen, Ashok Cutkosky |
| 2022 | ICML | PDE-Based Optimal Strategy for Unconstrained Online Learning. | Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis |
| 2021 | AISTATS | Power of Hints for Online Learning with Movement Costs. | Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit |
| 2021 | ICLR | Extreme Memorization via Scale of Initialization. | Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur |
| 2021 | ICML | Robust Pure Exploration in Linear Bandits with Limited Budget. | Ayya Alieva, Ashok Cutkosky, Abhimanyu Das |
| 2021 | ICML | Dynamic Balancing for Model Selection in Bandits and RL. | Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Claudio Gentile, Aldo Pacchiano, Manish Purohit |
| 2020 | ICML | Online Learning with Imperfect Hints. | Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit |
| 2020 | ICML | Parameter-free, Dynamic, and Strongly-Adaptive Online Learning. | Ashok Cutkosky |
| 2020 | ICML | Momentum Improves Normalized SGD. | Ashok Cutkosky, Harsh Mehta |
| 2019 | COLT | Artificial Constraints and Hints for Unbounded Online Learning. | Ashok Cutkosky |
| 2019 | COLT | Combining Online Learning Guarantees. | Ashok Cutkosky |
| 2019 | ICML | Anytime Online-to-Batch, Optimism and Acceleration. | Ashok Cutkosky |
| 2019 | ICML | Matrix-Free Preconditioning in Online Learning. | Ashok Cutkosky, Tams Sarls |
| 2019 | ICML | Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. | Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona |
| 2018 | COLT | Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. | Ashok Cutkosky, Francesco Orabona |
| 2017 | COLT | Online Learning Without Prior Information. | Ashok Cutkosky, Kwabena Boahen |