default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAshok Cutkosky
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c47]Zhiyu Zhang, Heng Yang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
Improving Adaptive Online Learning Using Refined Discretization. ALT 2024: 1208-1233- [c46]Qinzi Zhang, Hoang Tran, Ashok Cutkosky:
Private Zeroth-Order Nonsmooth Nonconvex Optimization. ICLR 2024 - [c45]Andrew Jacobsen, Ashok Cutkosky:
Online Linear Regression in Dynamic Environments via Discounting. ICML 2024 - [c44]Qinzi Zhang, Ashok Cutkosky:
Random Scaling and Momentum for Non-smooth Non-convex Optimization. ICML 2024 - [i48]Qinzi Zhang, Ashok Cutkosky:
Random Scaling and Momentum for Non-smooth Non-convex Optimization. CoRR abs/2405.09742 (2024) - [i47]Aaron Defazio, Xingyu Yang, Harsh Mehta, Konstantin Mishchenko, Ahmed Khaled, Ashok Cutkosky:
The Road Less Scheduled. CoRR abs/2405.15682 (2024) - [i46]Kwangjun Ahn, Ashok Cutkosky:
Adam with model exponential moving average is effective for nonconvex optimization. CoRR abs/2405.18199 (2024) - [i45]Andrew Jacobsen, Ashok Cutkosky:
Online Linear Regression in Dynamic Environments via Discounting. CoRR abs/2405.19175 (2024) - [i44]Ashok Cutkosky, Zakaria Mhammedi:
Fully Unconstrained Online Learning. CoRR abs/2405.20540 (2024) - [i43]Qinzi Zhang, Hoang Tran, Ashok Cutkosky:
Private Zeroth-Order Nonsmooth Nonconvex Optimization. CoRR abs/2406.19579 (2024) - [i42]Hoang Tran, Qinzi Zhang, Ashok Cutkosky:
Empirical Tests of Optimization Assumptions in Deep Learning. CoRR abs/2407.01825 (2024) - 2023
- [j3]Harsh Mehta, Walid Krichene, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky
:
Differentially Private Image Classification from Features. Trans. Mach. Learn. Res. 2023 (2023) - [j2]Harsh Mehta, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky:
Towards Large Scale Transfer Learning for Differentially Private Image Classification. Trans. Mach. Learn. Res. 2023 (2023) - [c43]Harsh Mehta, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur:
Long Range Language Modeling via Gated State Spaces. ICLR 2023 - [c42]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Bandit Online Linear Optimization with Hints and Queries. ICML 2023: 2313-2336 - [c41]Ashok Cutkosky, Harsh Mehta, Francesco Orabona:
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. ICML 2023: 6643-6670 - [c40]Andrew Jacobsen, Ashok Cutkosky:
Unconstrained Online Learning with Unbounded Losses. ICML 2023: 14590-14630 - [c39]Volkan Cevher, Ashok Cutkosky, Ali Kavis, Georgios Piliouras, Stratis Skoulakis, Luca Viano:
Alternation makes the adversary weaker in two-player games. NeurIPS 2023 - [c38]Ashok Cutkosky, Aaron Defazio, Harsh Mehta:
Mechanic: A Learning Rate Tuner. NeurIPS 2023 - [c37]Zhiyu Zhang, Ashok Cutkosky, Yannis Paschalidis:
Unconstrained Dynamic Regret via Sparse Coding. NeurIPS 2023 - [c36]Ashok Cutkosky, Abhimanyu Das, Weihao Kong, Chansoo Lee, Rajat Sen:
Blackbox optimization of unimodal functions. UAI 2023: 476-484 - [i41]Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
Unconstrained Dynamic Regret via Sparse Coding. CoRR abs/2301.13349 (2023) - [i40]Ashok Cutkosky, Harsh Mehta, Francesco Orabona:
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. CoRR abs/2302.03775 (2023) - [i39]Ashok Cutkosky, Aaron Defazio, Harsh Mehta:
Mechanic: A Learning Rate Tuner. CoRR abs/2306.00144 (2023) - [i38]Andrew Jacobsen, Ashok Cutkosky:
Unconstrained Online Learning with Unbounded Losses. CoRR abs/2306.04923 (2023) - [i37]Zhiyu Zhang, Heng Yang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
Improving Adaptive Online Learning Using Refined Discretization. CoRR abs/2309.16044 (2023) - [i36]Aaron Defazio, Ashok Cutkosky, Harsh Mehta, Konstantin Mishchenko:
When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement. CoRR abs/2310.07831 (2023) - 2022
- [j1]Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona:
Understanding AdamW through Proximal Methods and Scale-Freeness. Trans. Mach. Learn. Res. 2022 (2022) - [c35]Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory. AISTATS 2022: 8458-8492 - [c34]Keyi Chen, Ashok Cutkosky, Francesco Orabona:
Implicit Parameter-free Online Learning with Truncated Linear Models. ALT 2022: 148-175 - [c33]Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Qiuyi (Richard) Zhang:
Leveraging Initial Hints for Free in Stochastic Linear Bandits. ALT 2022: 282-318 - [c32]Andrew Jacobsen, Ashok Cutkosky:
Parameter-free Mirror Descent. COLT 2022: 4160-4211 - [c31]Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
PDE-Based Optimal Strategy for Unconstrained Online Learning. ICML 2022: 26085-26115 - [c30]Zhiyu Zhang, Ashok Cutkosky, Yannis Paschalidis:
Optimal Comparator Adaptive Online Learning with Switching Cost. NeurIPS 2022 - [c29]Hoang Tran, Ashok Cutkosky:
Better SGD using Second-order Momentum. NeurIPS 2022 - [c28]Hoang Tran, Ashok Cutkosky:
Momentum Aggregation for Private Non-convex ERM. NeurIPS 2022 - [c27]Jiujia Zhang, Ashok Cutkosky:
Parameter-free Regret in High Probability with Heavy Tails. NeurIPS 2022 - [c26]Qinzi Zhang, Hoang Tran, Ashok Cutkosky:
Differentially Private Online-to-batch for Smooth Losses. NeurIPS 2022 - [i35]Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
PDE-Based Optimal Strategy for Unconstrained Online Learning. CoRR abs/2201.07877 (2022) - [i34]Zhenxun Zhuang, Mingrui Liu, Ashok Cutkosky, Francesco Orabona:
Understanding AdamW through Proximal Methods and Scale-Freeness. CoRR abs/2202.00089 (2022) - [i33]Andrew Jacobsen, Ashok Cutkosky:
Parameter-free Mirror Descent. CoRR abs/2203.00444 (2022) - [i32]Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Qiuyi (Richard) Zhang:
Leveraging Initial Hints for Free in Stochastic Linear Bandits. CoRR abs/2203.04274 (2022) - [i31]Keyi Chen, Ashok Cutkosky, Francesco Orabona:
Implicit Parameter-free Online Learning with Truncated Linear Models. CoRR abs/2203.10327 (2022) - [i30]Harsh Mehta, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky:
Large Scale Transfer Learning for Differentially Private Image Classification. CoRR abs/2205.02973 (2022) - [i29]Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
Optimal Parameter-free Online Learning with Switching Cost. CoRR abs/2205.06846 (2022) - [i28]Harsh Mehta, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur:
Long Range Language Modeling via Gated State Spaces. CoRR abs/2206.13947 (2022) - [i27]Hoang Tran, Ashok Cutkosky:
Momentum Aggregation for Private Non-convex ERM. CoRR abs/2210.06328 (2022) - [i26]Qinzi Zhang, Hoang Tran, Ashok Cutkosky:
Differentially Private Online-to-Batch for Smooth Losses. CoRR abs/2210.06593 (2022) - [i25]Jiujia Zhang, Ashok Cutkosky:
Parameter-free Regret in High Probability with Heavy Tails. CoRR abs/2210.14355 (2022) - [i24]Harsh Mehta, Walid Krichene, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky:
Differentially Private Image Classification from Features. CoRR abs/2211.13403 (2022) - 2021
- [c25]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Power of Hints for Online Learning with Movement Costs. AISTATS 2021: 2818-2826 - [c24]Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur:
Extreme Memorization via Scale of Initialization. ICLR 2021 - [c23]Ayya Alieva, Ashok Cutkosky, Abhimanyu Das:
Robust Pure Exploration in Linear Bandits with Limited Budget. ICML 2021: 187-195 - [c22]Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Claudio Gentile, Aldo Pacchiano, Manish Purohit:
Dynamic Balancing for Model Selection in Bandits and RL. ICML 2021: 2276-2285 - [c21]Ashok Cutkosky, Harsh Mehta:
High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails. NeurIPS 2021: 4883-4895 - [c20]Aditya Gangrade, Anil Kag, Ashok Cutkosky, Venkatesh Saligrama:
Online Selective Classification with Limited Feedback. NeurIPS 2021: 14529-14541 - [c19]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Logarithmic Regret from Sublinear Hints. NeurIPS 2021: 28222-28232 - [i23]Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis:
Strongly Adaptive OCO with Memory. CoRR abs/2102.01623 (2021) - [i22]Hoang Tran, Ashok Cutkosky:
Correcting Momentum with Second-order Information. CoRR abs/2103.03265 (2021) - [i21]Ashok Cutkosky, Harsh Mehta:
High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails. CoRR abs/2106.14343 (2021) - [i20]Aditya Gangrade, Anil Kag, Ashok Cutkosky, Venkatesh Saligrama:
Online Selective Classification with Limited Feedback. CoRR abs/2110.14243 (2021) - [i19]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Logarithmic Regret from Sublinear Hints. CoRR abs/2111.05257 (2021) - 2020
- [c18]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Online Learning with Imperfect Hints. ICML 2020: 822-831 - [c17]Ashok Cutkosky:
Parameter-free, Dynamic, and Strongly-Adaptive Online Learning. ICML 2020: 2250-2259 - [c16]Ashok Cutkosky, Harsh Mehta:
Momentum Improves Normalized SGD. ICML 2020: 2260-2268 - [c15]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Online Linear Optimization with Many Hints. NeurIPS 2020 - [c14]Ashok Cutkosky:
Better Full-Matrix Regret via Parameter-Free Online Learning. NeurIPS 2020 - [c13]Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo:
Comparator-Adaptive Convex Bandits. NeurIPS 2020 - [i18]Ashok Cutkosky, Harsh Mehta:
Momentum Improves Normalized SGD. CoRR abs/2002.03305 (2020) - [i17]Ashok Cutkosky:
Adaptive Online Learning with Varying Norms. CoRR abs/2002.03963 (2020) - [i16]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Online Learning with Imperfect Hints. CoRR abs/2002.04726 (2020) - [i15]Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo:
Comparator-adaptive Convex Bandits. CoRR abs/2007.08448 (2020) - [i14]Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur:
Extreme Memorization via Scale of Initialization. CoRR abs/2008.13363 (2020) - [i13]Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit:
Online Linear Optimization with Many Hints. CoRR abs/2010.03082 (2020) - [i12]Ashok Cutkosky, Abhimanyu Das, Manish Purohit:
Upper Confidence Bounds for Combining Stochastic Bandits. CoRR abs/2012.13115 (2020)
2010 – 2019
- 2019
- [c12]Ashok Cutkosky:
Artificial Constraints and Hints for Unbounded Online Learning. COLT 2019: 874-894 - [c11]Ashok Cutkosky:
Combining Online Learning Guarantees. COLT 2019: 895-913 - [c10]Ashok Cutkosky:
Anytime Online-to-Batch, Optimism and Acceleration. ICML 2019: 1446-1454 - [c9]Ashok Cutkosky, Tamás Sarlós:
Matrix-Free Preconditioning in Online Learning. ICML 2019: 1455-1464 - [c8]Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona:
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. ICML 2019: 7664-7672 - [c7]Ashok Cutkosky, Francesco Orabona:
Momentum-Based Variance Reduction in Non-Convex SGD. NeurIPS 2019: 15210-15219 - [c6]Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona:
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. NeurIPS 2019: 15332-15341 - [i11]Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona:
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization. CoRR abs/1901.09068 (2019) - [i10]Ashok Cutkosky:
Combining Online Learning Guarantees. CoRR abs/1902.09003 (2019) - [i9]Ashok Cutkosky:
Artificial Constraints and Lipschitz Hints for Unconstrained Online Learning. CoRR abs/1902.09013 (2019) - [i8]Ashok Cutkosky:
Anytime Online-to-Batch Conversions, Optimism, and Acceleration. CoRR abs/1903.00974 (2019) - [i7]Ashok Cutkosky, Francesco Orabona:
Momentum-Based Variance Reduction in Non-Convex SGD. CoRR abs/1905.10018 (2019) - [i6]Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona:
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. CoRR abs/1905.10680 (2019) - [i5]Ashok Cutkosky, Tamás Sarlós:
Matrix-Free Preconditioning in Online Learning. CoRR abs/1905.12721 (2019) - 2018
- [b1]Ashok Cutkosky:
Algorithms and lower bounds for parameter-free online learning. Stanford University, USA, 2018 - [c5]Ashok Cutkosky, Francesco Orabona:
Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. COLT 2018: 1493-1529 - [c4]Ashok Cutkosky, Róbert Busa-Fekete:
Distributed Stochastic Optimization via Adaptive SGD. NeurIPS 2018: 1914-1923 - [i4]Ashok Cutkosky, Róbert Busa-Fekete:
Distributed Stochastic Optimization via Adaptive Stochastic Gradient Descent. CoRR abs/1802.05811 (2018) - [i3]Ashok Cutkosky, Francesco Orabona:
Black-Box Reductions for Parameter-free Online Learning in Banach Spaces. CoRR abs/1802.06293 (2018) - 2017
- [c3]Ashok Cutkosky, Kwabena Boahen:
Online Learning Without Prior Information. COLT 2017: 643-677 - [c2]Ashok Cutkosky, Kwabena Boahen:
Stochastic and Adversarial Online Learning without Hyperparameters. NIPS 2017: 5059-5067 - [i2]Ashok Cutkosky, Kwabena Boahen:
Online Convex Optimization with Unconstrained Domains and Losses. CoRR abs/1703.02622 (2017) - [i1]Ashok Cutkosky, Kwabena Boahen:
Online Learning Without Prior Information. CoRR abs/1703.02629 (2017) - 2016
- [c1]Ashok Cutkosky, Kwabena Boahen:
Online Convex Optimization with Unconstrained Domains and Losses. NIPS 2016: 748-756
Coauthor Index
aka: Yannis Paschalidis
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-09-04 01:25 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
