default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDUmut Simsekli
- > Home > Persons > Umut Simsekli
Publications
- 2025
[i61]Thanh Dang, Melih Barsbey, A K. M. Rokonuzzaman Sonet, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu:
Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise. CoRR abs/2502.00885 (2025)- 2024
- [i52]Umut Simsekli, Mert Gürbüzbalaban, Sinan Yildirim, Lingjiong Zhu:
Differential Privacy of Noisy (S)GD under Heavy-Tailed Perturbations. CoRR abs/2403.02051 (2024) - 2023
- [j11]Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu:
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize. Trans. Mach. Learn. Res. 2023 (2023) - [c69]Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli:
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. ALT 2023: 1292-1342 - [c66]Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli:
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions. ICML 2023: 28578-28597 - [c62]Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli:
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent. NeurIPS 2023 - [i47]Anant Raj
, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli:
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions. CoRR abs/2301.11885 (2023) - [i45]Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu:
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD. CoRR abs/2302.05516 (2023) - [i43]Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli:
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent. CoRR abs/2305.12056 (2023) - 2022
- [j10]Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu:
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks. J. Mach. Learn. Res. 23: 220:1-220:96 (2022) - [i36]Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Kun Yuan, Lingjiong Zhu:
Heavy-Tail Phenomenon in Decentralized SGD. CoRR abs/2205.06689 (2022) - [i34]Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli:
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. CoRR abs/2206.01274 (2022) - 2021
- [c55]Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli:
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections. ICML 2021: 1249-1260 - [c54]Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu:
The Heavy-Tail Phenomenon in SGD. ICML 2021: 3964-3975 - [c50]Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu:
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms. NeurIPS 2021: 18774-18788 - [c49]Hongjian Wang, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli, Murat A. Erdogdu:
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance. NeurIPS 2021: 18866-18877 - [i31]Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli:
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections. CoRR abs/2102.07006 (2021) - [i28]Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu:
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms. CoRR abs/2106.04881 (2021) - 2020
- [c45]Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban:
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise. ICML 2020: 8970-8980 - [i24]Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban:
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise. CoRR abs/2002.05685 (2020) - [i20]Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu:
The Heavy-Tail Phenomenon in SGD. CoRR abs/2006.04740 (2020) - 2019
- [c35]Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban:
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. ICML 2019: 5827-5837 - [c31]Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard:
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise. NeurIPS 2019: 273-283 - [i16]Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban:
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. CoRR abs/1901.06053 (2019) - [i9]Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard:
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise. CoRR abs/1906.09069 (2019) - [i7]Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu:
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks. CoRR abs/1910.08701 (2019) - [i6]Umut Simsekli, Mert Gürbüzbalaban, Thanh Huy Nguyen, Gaël Richard, Levent Sagun:
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks. CoRR abs/1912.00018 (2019)
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 2025-08-21 01:56 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:
