default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSoufiane Hayou
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
Books and Theses
- 2021
[b1]Soufiane Hayou:
Wide deep neural networks. University of Oxford, UK, 2021
Journal Articles
- 2023
- [j3]Fadhel Ayed, Soufiane Hayou:
Data pruning and neural scaling laws: fundamental limitations of score-based algorithms. Trans. Mach. Learn. Res. 2023 (2023) - [j2]Soufiane Hayou:
On the infinite-depth limit of finite-width neural networks. Trans. Mach. Learn. Res. 2023 (2023) - 2022
- [j1]Fusheng Liu, Haizhao Yang, Soufiane Hayou, Qianxiao Li:
From Optimization Dynamics to Generalization Bounds via Łojasiewicz Gradient Inequality. Trans. Mach. Learn. Res. 2022 (2022)
Conference and Workshop Papers
- 2024
- [c10]Jiayuan Ye, Anastasia Borovykh, Soufiane Hayou, Reza Shokri:
Leave-one-out Distinguishability in Machine Learning. ICLR 2024 - [c9]Greg Yang, Dingli Yu, Chen Zhu, Soufiane Hayou:
Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks. ICLR 2024 - [c8]Soufiane Hayou, Nikhil Ghosh, Bin Yu:
LoRA+: Efficient Low Rank Adaptation of Large Models. ICML 2024 - 2023
- [c7]Soufiane Hayou, Greg Yang:
Width and Depth Limits Commute in Residual Networks. ICML 2023: 12700-12723 - 2022
- [c6]Yizhang Lou, Chris E. Mingard, Soufiane Hayou:
Feature Learning and Signal Propagation in Deep Neural Networks. ICML 2022: 14248-14282 - 2021
- [c5]Soufiane Hayou, Eugenio Clerico, Bobby He, George Deligiannidis, Arnaud Doucet, Judith Rousseau:
Stable ResNet. AISTATS 2021: 1324-1332 - [c4]Soufiane Hayou, Arnaud Doucet, Judith Rousseau:
The Curse of Depth in Kernel Regime. ICBINB@NeurIPS 2021: 41-47 - [c3]Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh:
Robust Pruning at Initialization. ICLR 2021 - [c2]Soufiane Hayou, Fadhel Ayed:
Regularization in ResNet with Stochastic Depth. NeurIPS 2021: 15464-15474 - 2019
- [c1]Soufiane Hayou, Arnaud Doucet, Judith Rousseau:
On the Impact of the Activation function on Deep Neural Networks Training. ICML 2019: 2672-2680
Informal and Other Publications
- 2024
- [i19]Soufiane Hayou, Nikhil Ghosh, Bin Yu:
LoRA+: Efficient Low Rank Adaptation of Large Models. CoRR abs/2402.12354 (2024) - [i18]Mohamed El Amine Seddik, Suei-Wen Chen, Soufiane Hayou, Pierre Youssef, Mérouane Debbah:
How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse. CoRR abs/2404.05090 (2024) - [i17]Soufiane Hayou, Nikhil Ghosh, Bin Yu:
The Impact of Initialization on LoRA Finetuning Dynamics. CoRR abs/2406.08447 (2024) - 2023
- [i16]Soufiane Hayou, Greg Yang:
Width and Depth Limits Commute in Residual Networks. CoRR abs/2302.00453 (2023) - [i15]Fadhel Ayed, Soufiane Hayou:
Data pruning and neural scaling laws: fundamental limitations of score-based algorithms. CoRR abs/2302.06960 (2023) - [i14]Soufiane Hayou:
On the Connection Between Riemann Hypothesis and a Special Class of Neural Networks. CoRR abs/2309.09171 (2023) - [i13]Jiayuan Ye, Anastasia Borovykh, Soufiane Hayou, Reza Shokri:
Leave-one-out Distinguishability in Machine Learning. CoRR abs/2309.17310 (2023) - [i12]Soufiane Hayou:
Commutative Width and Depth Scaling in Deep Neural Networks. CoRR abs/2310.01683 (2023) - [i11]Greg Yang, Dingli Yu, Chen Zhu, Soufiane Hayou:
Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks. CoRR abs/2310.02244 (2023) - 2022
- [i10]Fusheng Liu, Haizhao Yang, Soufiane Hayou, Qianxiao Li:
Connecting Optimization and Generalization via Gradient Flow Path Length. CoRR abs/2202.10670 (2022) - [i9]Soufiane Hayou:
On the infinite-depth limit of finite-width neural networks. CoRR abs/2210.00688 (2022) - 2021
- [i8]Soufiane Hayou, Fadhel Ayed:
Regularization in ResNet with Stochastic Depth. CoRR abs/2106.03091 (2021) - [i7]Yizhang Lou, Chris Mingard, Soufiane Hayou:
The Equilibrium Hypothesis: Rethinking implicit regularization in Deep Neural Networks. CoRR abs/2110.11749 (2021) - [i6]Soufiane Hayou, Bobby He, Gintare Karolina Dziugaite:
Probabilistic fine-tuning of pruning masks and PAC-Bayes self-bounded learning. CoRR abs/2110.11804 (2021) - 2020
- [i5]Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh:
Pruning untrained neural networks: Principles and Analysis. CoRR abs/2002.08797 (2020) - [i4]Soufiane Hayou, Eugenio Clerico, Bobby He, George Deligiannidis, Arnaud Doucet, Judith Rousseau:
Stable ResNet. CoRR abs/2010.12859 (2020) - 2019
- [i3]Soufiane Hayou, Arnaud Doucet, Judith Rousseau:
On the Impact of the Activation Function on Deep Neural Networks Training. CoRR abs/1902.06853 (2019) - [i2]Soufiane Hayou, Arnaud Doucet, Judith Rousseau:
Training Dynamics of Deep Networks using Stochastic Gradient Descent via Neural Tangent Kernel. CoRR abs/1905.13654 (2019) - 2018
- [i1]Soufiane Hayou, Arnaud Doucet, Judith Rousseau:
On the Selection of Initialization and Activation Function for Deep Neural Networks. CoRR abs/1805.08266 (2018)
Coauthor Index
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:
