Ashok Cutkosky

Orcid: 0000-0002-3822-3029

According to our database1, Ashok Cutkosky authored at least 65 papers between 2016 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Empirical Tests of Optimization Assumptions in Deep Learning.
CoRR, 2024

Fully Unconstrained Online Learning.
CoRR, 2024

Adam with model exponential moving average is effective for nonconvex optimization.
CoRR, 2024

The Road Less Scheduled.
CoRR, 2024

Random Scaling and Momentum for Non-smooth Non-convex Optimization.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Online Linear Regression in Dynamic Environments via Discounting.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Private Zeroth-Order Nonsmooth Nonconvex Optimization.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Improving Adaptive Online Learning Using Refined Discretization.
Proceedings of the International Conference on Algorithmic Learning Theory, 2024

2023
Towards Large Scale Transfer Learning for Differentially Private Image Classification.
Trans. Mach. Learn. Res., 2023

Differentially Private Image Classification from Features.
Trans. Mach. Learn. Res., 2023

When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement.
CoRR, 2023

Blackbox optimization of unimodal functions.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

Unconstrained Dynamic Regret via Sparse Coding.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mechanic: A Learning Rate Tuner.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Alternation makes the adversary weaker in two-player games.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Unconstrained Online Learning with Unbounded Losses.
Proceedings of the International Conference on Machine Learning, 2023

Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion.
Proceedings of the International Conference on Machine Learning, 2023

Bandit Online Linear Optimization with Hints and Queries.
Proceedings of the International Conference on Machine Learning, 2023

Long Range Language Modeling via Gated State Spaces.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Understanding AdamW through Proximal Methods and Scale-Freeness.
Trans. Mach. Learn. Res., 2022

Optimal Parameter-free Online Learning with Switching Cost.
CoRR, 2022

Large Scale Transfer Learning for Differentially Private Image Classification.
CoRR, 2022

Differentially Private Online-to-batch for Smooth Losses.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Parameter-free Regret in High Probability with Heavy Tails.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Momentum Aggregation for Private Non-convex ERM.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Better SGD using Second-order Momentum.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Optimal Comparator Adaptive Online Learning with Switching Cost.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

PDE-Based Optimal Strategy for Unconstrained Online Learning.
Proceedings of the International Conference on Machine Learning, 2022

Parameter-free Mirror Descent.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Leveraging Initial Hints for Free in Stochastic Linear Bandits.
Proceedings of the International Conference on Algorithmic Learning Theory, 29 March, 2022

Implicit Parameter-free Online Learning with Truncated Linear Models.
Proceedings of the International Conference on Algorithmic Learning Theory, 29 March, 2022

Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021
Correcting Momentum with Second-order Information.
CoRR, 2021

Strongly Adaptive OCO with Memory.
CoRR, 2021

Online Selective Classification with Limited Feedback.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Logarithmic Regret from Sublinear Hints.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Dynamic Balancing for Model Selection in Bandits and RL.
Proceedings of the 38th International Conference on Machine Learning, 2021

Robust Pure Exploration in Linear Bandits with Limited Budget.
Proceedings of the 38th International Conference on Machine Learning, 2021

Extreme Memorization via Scale of Initialization.
Proceedings of the 9th International Conference on Learning Representations, 2021

Power of Hints for Online Learning with Movement Costs.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Upper Confidence Bounds for Combining Stochastic Bandits.
CoRR, 2020

Adaptive Online Learning with Varying Norms.
CoRR, 2020

Comparator-Adaptive Convex Bandits.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Better Full-Matrix Regret via Parameter-Free Online Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Online Linear Optimization with Many Hints.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Momentum Improves Normalized SGD.
Proceedings of the 37th International Conference on Machine Learning, 2020

Parameter-free, Dynamic, and Strongly-Adaptive Online Learning.
Proceedings of the 37th International Conference on Machine Learning, 2020

Online Learning with Imperfect Hints.
Proceedings of the 37th International Conference on Machine Learning, 2020

2019
Anytime Online-to-Batch Conversions, Optimism, and Acceleration.
CoRR, 2019

Artificial Constraints and Lipschitz Hints for Unconstrained Online Learning.
CoRR, 2019

Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Momentum-Based Variance Reduction in Non-Convex SGD.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization.
Proceedings of the 36th International Conference on Machine Learning, 2019

Matrix-Free Preconditioning in Online Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019

Anytime Online-to-Batch, Optimism and Acceleration.
Proceedings of the 36th International Conference on Machine Learning, 2019

Combining Online Learning Guarantees.
Proceedings of the Conference on Learning Theory, 2019

Artificial Constraints and Hints for Unbounded Online Learning.
Proceedings of the Conference on Learning Theory, 2019

2018
Algorithms and lower bounds for parameter-free online learning.
PhD thesis, 2018

Distributed Stochastic Optimization via Adaptive Stochastic Gradient Descent.
CoRR, 2018

Distributed Stochastic Optimization via Adaptive SGD.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Black-Box Reductions for Parameter-free Online Learning in Banach Spaces.
Proceedings of the Conference On Learning Theory, 2018

2017
Stochastic and Adversarial Online Learning without Hyperparameters.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Online Learning Without Prior Information.
Proceedings of the 30th Conference on Learning Theory, 2017

2016
Online Convex Optimization with Unconstrained Domains and Losses.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016


  Loading...