Ashok Cutkosky

108 papers A* 45A 3B 3Journal 54Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Pretraining improves prediction of genomic datasets across species. Bioinform. Fangrui Huang, Yitong Wang, Ashok Cutkosky, Janet H. T. Song
2025	A*	`conf`	Descent with Misaligned Gradients and Applications to Hidden Convexity. ICLR Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2025	A*	`conf`	General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization. ICML Kwangjun Ahn, Gagik Magakyan, Ashok Cutkosky
2025	A*	`conf`	Unconstrained Robust Online Convex Optimization. ICML Jiujia Zhang, Ashok Cutkosky
2025	J	`jnl`	Unconstrained Robust Online Convex Optimization. CoRR Jiujia Zhang, Ashok Cutkosky
2024	A*	`conf`	Adam with model exponential moving average is effective for nonconvex optimization. NeurIPS Kwangjun Ahn, Ashok Cutkosky
2024	J	`jnl`	Adam with model exponential moving average is effective for nonconvex optimization. CoRR Kwangjun Ahn, Ashok Cutkosky
2024	J	`jnl`	Empirical Tests of Optimization Assumptions in Deep Learning. CoRR Hoang Tran, Qinzi Zhang, Ashok Cutkosky
2024	A*	`conf`	Fully Unconstrained Online Learning. NeurIPS Ashok Cutkosky, Zakaria Mhammedi
2024	J	`jnl`	Fully Unconstrained Online Learning. CoRR Ashok Cutkosky, Zakaria Mhammedi
2024	J	`jnl`	General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization. CoRR Kwangjun Ahn, Gagik Magakyan, Ashok Cutkosky
2024	B	`conf`	Improving Adaptive Online Learning Using Refined Discretization. ALT Zhiyu Zhang, Heng Yang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2024	A*	`conf`	Online Linear Regression in Dynamic Environments via Discounting. ICML Andrew Jacobsen, Ashok Cutkosky
2024	J	`jnl`	Online Linear Regression in Dynamic Environments via Discounting. CoRR Andrew Jacobsen, Ashok Cutkosky
2024	A*	`conf`	Private Zeroth-Order Nonsmooth Nonconvex Optimization. ICLR Qinzi Zhang, Hoang Tran, Ashok Cutkosky
2024	J	`jnl`	Private Zeroth-Order Nonsmooth Nonconvex Optimization. CoRR Qinzi Zhang, Hoang Tran, Ashok Cutkosky
2024	A*	`conf`	Random Scaling and Momentum for Non-smooth Non-convex Optimization. ICML Qinzi Zhang, Ashok Cutkosky
2024	J	`jnl`	Random Scaling and Momentum for Non-smooth Non-convex Optimization. CoRR Qinzi Zhang, Ashok Cutkosky
2024	A*	`conf`	The Road Less Scheduled. NeurIPS Aaron Defazio, Xingyu Yang, Ahmed Khaled, Konstantin Mishchenko, Harsh Mehta, Ashok Cutkosky
2024	J	`jnl`	The Road Less Scheduled. CoRR Aaron Defazio, Xingyu Yang, Harsh Mehta, Konstantin Mishchenko, Ahmed Khaled, Ashok Cutkosky
2023	A*	`conf`	Alternation makes the adversary weaker in two-player games. NeurIPS Volkan Cevher, Ashok Cutkosky, Ali Kavis, Georgios Piliouras, Stratis Skoulakis, Luca Viano
2023	A*	`conf`	Bandit Online Linear Optimization with Hints and Queries. ICML Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2023	A	`conf`	Blackbox optimization of unimodal functions. UAI Ashok Cutkosky, Abhimanyu Das, Weihao Kong, Chansoo Lee, Rajat Sen
2023	J	`jnl`	Differentially Private Image Classification from Features. Trans. Mach. Learn. Res. Harsh Mehta, Walid Krichene, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky
2023	J	`jnl`	Improving Adaptive Online Learning Using Refined Discretization. CoRR Zhiyu Zhang, Heng Yang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2023	A*	`conf`	Long Range Language Modeling via Gated State Spaces. ICLR Harsh Mehta, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur
2023	A*	`conf`	Mechanic: A Learning Rate Tuner. NeurIPS Ashok Cutkosky, Aaron Defazio, Harsh Mehta
2023	J	`jnl`	Mechanic: A Learning Rate Tuner. CoRR Ashok Cutkosky, Aaron Defazio, Harsh Mehta
2023	A*	`conf`	Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. ICML Ashok Cutkosky, Harsh Mehta, Francesco Orabona
2023	J	`jnl`	Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. CoRR Ashok Cutkosky, Harsh Mehta, Francesco Orabona
2023	J	`jnl`	Towards Large Scale Transfer Learning for Differentially Private Image Classification. Trans. Mach. Learn. Res. Harsh Mehta, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky
2023	A*	`conf`	Unconstrained Dynamic Regret via Sparse Coding. NeurIPS Zhiyu Zhang, Ashok Cutkosky, Yannis Paschalidis
2023	J	`jnl`	Unconstrained Dynamic Regret via Sparse Coding. CoRR Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2023	A*	`conf`	Unconstrained Online Learning with Unbounded Losses. ICML Andrew Jacobsen, Ashok Cutkosky
2023	J	`jnl`	Unconstrained Online Learning with Unbounded Losses. CoRR Andrew Jacobsen, Ashok Cutkosky
2023	J	`jnl`	When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement. CoRR Aaron Defazio, Ashok Cutkosky, Harsh Mehta, Konstantin Mishchenko
2022	A	`conf`	Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory. AISTATS Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2022	A*	`conf`	Better SGD using Second-order Momentum. NeurIPS Hoang Tran, Ashok Cutkosky
2022	J	`jnl`	Differentially Private Image Classification from Features. CoRR Harsh Mehta, Walid Krichene, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky
2022	J	`jnl`	Differentially Private Online-to-Batch for Smooth Losses. CoRR Qinzi Zhang, Hoang Tran, Ashok Cutkosky
2022	A*	`conf`	Differentially Private Online-to-batch for Smooth Losses. NeurIPS Qinzi Zhang, Hoang Tran, Ashok Cutkosky
2022	B	`conf`	Implicit Parameter-free Online Learning with Truncated Linear Models. ALT Keyi Chen, Ashok Cutkosky, Francesco Orabona
2022	J	`jnl`	Implicit Parameter-free Online Learning with Truncated Linear Models. CoRR Keyi Chen, Ashok Cutkosky, Francesco Orabona
2022	J	`jnl`	Large Scale Transfer Learning for Differentially Private Image Classification. CoRR Harsh Mehta, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky
2022	B	`conf`	Leveraging Initial Hints for Free in Stochastic Linear Bandits. ALT Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Qiuyi (Richard) Zhang
2022	J	`jnl`	Leveraging Initial Hints for Free in Stochastic Linear Bandits. CoRR Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Qiuyi (Richard) Zhang
2022	J	`jnl`	Long Range Language Modeling via Gated State Spaces. CoRR Harsh Mehta, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur
2022	A*	`conf`	Momentum Aggregation for Private Non-convex ERM. NeurIPS Hoang Tran, Ashok Cutkosky
2022	J	`jnl`	Momentum Aggregation for Private Non-convex ERM. CoRR Hoang Tran, Ashok Cutkosky
2022	A*	`conf`	Optimal Comparator Adaptive Online Learning with Switching Cost. NeurIPS Zhiyu Zhang, Ashok Cutkosky, Yannis Paschalidis
2022	J	`jnl`	Optimal Parameter-free Online Learning with Switching Cost. CoRR Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2022	A*	`conf`	PDE-Based Optimal Strategy for Unconstrained Online Learning. ICML Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2022	J	`jnl`	PDE-Based Optimal Strategy for Unconstrained Online Learning. CoRR Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2022	A*	`conf`	Parameter-free Mirror Descent. COLT Andrew Jacobsen, Ashok Cutkosky
2022	J	`jnl`	Parameter-free Mirror Descent. CoRR Andrew Jacobsen, Ashok Cutkosky
2022	A*	`conf`	Parameter-free Regret in High Probability with Heavy Tails. NeurIPS Jiujia Zhang, Ashok Cutkosky
2022	J	`jnl`	Parameter-free Regret in High Probability with Heavy Tails. CoRR Jiujia Zhang, Ashok Cutkosky
2022	J	`jnl`	Understanding AdamW through Proximal Methods and Scale-Freeness. CoRR Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona
2022	J	`jnl`	Understanding AdamW through Proximal Methods and Scale-Freeness. Trans. Mach. Learn. Res. Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona
2021	J	`jnl`	Correcting Momentum with Second-order Information. CoRR Hoang Tran, Ashok Cutkosky
2021	A*	`conf`	Dynamic Balancing for Model Selection in Bandits and RL. ICML Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Claudio Gentile, Aldo Pacchiano, Manish Purohit
2021	A*	`conf`	Extreme Memorization via Scale of Initialization. ICLR Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur
2021	A*	`conf`	High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails. NeurIPS Ashok Cutkosky, Harsh Mehta
2021	J	`jnl`	High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails. CoRR Ashok Cutkosky, Harsh Mehta
2021	A*	`conf`	Logarithmic Regret from Sublinear Hints. NeurIPS Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2021	J	`jnl`	Logarithmic Regret from Sublinear Hints. CoRR Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2021	A*	`conf`	Online Selective Classification with Limited Feedback. NeurIPS Aditya Gangrade, Anil Kag, Ashok Cutkosky, Venkatesh Saligrama
2021	J	`jnl`	Online Selective Classification with Limited Feedback. CoRR Aditya Gangrade, Anil Kag, Ashok Cutkosky, Venkatesh Saligrama
2021	A	`conf`	Power of Hints for Online Learning with Movement Costs. AISTATS Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2021	A*	`conf`	Robust Pure Exploration in Linear Bandits with Limited Budget. ICML Ayya Alieva, Ashok Cutkosky, Abhimanyu Das
2021	J	`jnl`	Strongly Adaptive OCO with Memory. CoRR Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2020	J	`jnl`	Adaptive Online Learning with Varying Norms. CoRR Ashok Cutkosky
2020	A*	`conf`	Better Full-Matrix Regret via Parameter-Free Online Learning. NeurIPS Ashok Cutkosky
2020	A*	`conf`	Comparator-Adaptive Convex Bandits. NeurIPS Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo
2020	J	`jnl`	Comparator-adaptive Convex Bandits. CoRR Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo
2020	J	`jnl`	Extreme Memorization via Scale of Initialization. CoRR Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur
2020	A*	`conf`	Momentum Improves Normalized SGD. ICML Ashok Cutkosky, Harsh Mehta
2020	J	`jnl`	Momentum Improves Normalized SGD. CoRR Ashok Cutkosky, Harsh Mehta
2020	A*	`conf`	Online Learning with Imperfect Hints. ICML Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2020	J	`jnl`	Online Learning with Imperfect Hints. CoRR Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2020	A*	`conf`	Online Linear Optimization with Many Hints. NeurIPS Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2020	J	`jnl`	Online Linear Optimization with Many Hints. CoRR Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
2020	A*	`conf`	Parameter-free, Dynamic, and Strongly-Adaptive Online Learning. ICML Ashok Cutkosky
2020	J	`jnl`	Upper Confidence Bounds for Combining Stochastic Bandits. CoRR Ashok Cutkosky, Abhimanyu Das, Manish Purohit
2019	J	`jnl`	Anytime Online-to-Batch Conversions, Optimism, and Acceleration. CoRR Ashok Cutkosky
2019	A*	`conf`	Anytime Online-to-Batch, Optimism and Acceleration. ICML Ashok Cutkosky
2019	A*	`conf`	Artificial Constraints and Hints for Unbounded Online Learning. COLT Ashok Cutkosky
2019	J	`jnl`	Artificial Constraints and Lipschitz Hints for Unconstrained Online Learning. CoRR Ashok Cutkosky
2019	A*	`conf`	Combining Online Learning Guarantees. COLT Ashok Cutkosky
2019	J	`jnl`	Combining Online Learning Guarantees. CoRR Ashok Cutkosky
2019	A*	`conf`	Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. NeurIPS Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
2019	J	`jnl`	Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. CoRR Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
2019	A*	`conf`	Matrix-Free Preconditioning in Online Learning. ICML Ashok Cutkosky, Tamás Sarlós
2019	J	`jnl`	Matrix-Free Preconditioning in Online Learning. CoRR Ashok Cutkosky, Tamás Sarlós
2019	A*	`conf`	Momentum-Based Variance Reduction in Non-Convex SGD. NeurIPS Ashok Cutkosky, Francesco Orabona
2019	J	`jnl`	Momentum-Based Variance Reduction in Non-Convex SGD. CoRR Ashok Cutkosky, Francesco Orabona
2019	A*	`conf`	Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. ICML Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona
2019	J	`jnl`	Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. CoRR Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona
2018	—	`—`	Algorithms and lower bounds for parameter-free online learning. Ashok Cutkosky
2018	A*	`conf`	Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. COLT Ashok Cutkosky, Francesco Orabona
2018	J	`jnl`	Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. CoRR Ashok Cutkosky, Francesco Orabona
2018	A*	`conf`	Distributed Stochastic Optimization via Adaptive SGD. NeurIPS Ashok Cutkosky, Róbert Busa-Fekete
2018	J	`jnl`	Distributed Stochastic Optimization via Adaptive Stochastic Gradient Descent. CoRR Ashok Cutkosky, Róbert Busa-Fekete
2017	J	`jnl`	Online Convex Optimization with Unconstrained Domains and Losses. CoRR Ashok Cutkosky, Kwabena Boahen
2017	A*	`conf`	Online Learning Without Prior Information. COLT Ashok Cutkosky, Kwabena Boahen
2017	J	`jnl`	Online Learning Without Prior Information. CoRR Ashok Cutkosky, Kwabena Boahen
2017	—	`conf`	Stochastic and Adversarial Online Learning without Hyperparameters. NIPS Ashok Cutkosky, Kwabena Boahen
2016	—	`conf`	Online Convex Optimization with Unconstrained Domains and Losses. NIPS Ashok Cutkosky, Kwabena Boahen