default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBoris Hanin
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c11]Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan:
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit. ICLR 2024- [c10]Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin:
Principled Architecture-aware Scaling of Hyperparameters. ICLR 2024 - [i28]Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin:
Principled Architecture-aware Scaling of Hyperparameters. CoRR abs/2402.17440 (2024) - [i27]Lingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Ion Stoica, Matei Zaharia, James Zou:
Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems. CoRR abs/2403.02419 (2024) - [i26]Boris Hanin, Alexander Zlokapa:
Bayesian Inference with Deep Weakly Nonlinear Networks. CoRR abs/2405.16630 (2024) - [i25]Jared Quincy Davis, Boris Hanin, Lingjiao Chen, Peter Bailis, Ion Stoica, Matei Zaharia:
Networks of Networks: Complexity Class Principles Applied to Compound AI Systems Design. CoRR abs/2407.16831 (2024) - [i24]Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin:
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization. CoRR abs/2410.08847 (2024) - 2023
- [c9]Gaurav Iyer, Boris Hanin, David Rolnick:
Maximal Initial Learning Rates in Deep ReLU Networks. ICML 2023: 14500-14530 - [i23]Samy Jelassi, Boris Hanin, Ziwei Ji, Sashank J. Reddi, Srinadh Bhojanapalli, Sanjiv Kumar:
Depth Dependence of μP Learning Rates in ReLU MLPs. CoRR abs/2305.07810 (2023) - [i22]Gage DeZoort, Boris Hanin:
Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations. CoRR abs/2306.11668 (2023) - [i21]Stefano Favaro, Boris Hanin, Domenico Marinucci, Ivan Nourdin, Giovanni Peccati:
Quantitative CLTs in Deep Neural Networks. CoRR abs/2307.06092 (2023) - [i20]Yasaman Bahri, Boris Hanin, Antonin Brossollet, Vittorio Erba, Christian Keup, Rosalba Pacelli, James B. Simon:
Les Houches Lectures on Deep Learning at Large & Infinite Width. CoRR abs/2309.01592 (2023) - [i19]Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan:
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit. CoRR abs/2309.16620 (2023) - 2022
- [c8]Boris Hanin, Ryan S. Jeong, David Rolnick:
Deep ReLU Networks Preserve Expected Length. ICLR 2022 - [c7]Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang:
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis. NeurIPS 2022 - [i18]Boris Hanin:
Correlation Functions in Random Fully Connected Neural Networks at Finite Width. CoRR abs/2204.01058 (2022) - [i17]Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang:
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis. CoRR abs/2205.05662 (2022) - [i16]Gaurav Iyer, Boris Hanin, David Rolnick
:
Maximal Initial Learning Rates in Deep ReLU Networks. CoRR abs/2212.07295 (2022) - [i15]Boris Hanin, Alexander Zlokapa:
Bayesian Interpolation with Deep Linear Networks. CoRR abs/2212.14457 (2022) - 2021
- [j1]Ronald A. DeVore, Boris Hanin, Guergana Petrova:
Neural network approximation. Acta Numer. 30: 327-444 (2021) - [c6]Boris Hanin, Yi Sun:
How Data Augmentation affects Optimization for Linear Regression. NeurIPS 2021: 8095-8105 - [i14]Boris Hanin, Ryan Jeong, David Rolnick:
Deep ReLU Networks Preserve Expected Length. CoRR abs/2102.10492 (2021) - [i13]Daniel A. Roberts, Sho Yaida, Boris Hanin:
The Principles of Deep Learning Theory. CoRR abs/2106.10165 (2021) - [i12]Boris Hanin:
Random Neural Networks in the Infinite Width Limit as Gaussian Processes. CoRR abs/2107.01562 (2021) - [i11]Boris Hanin:
Ridgeless Interpolation with Shallow ReLU Networks in $1D$ is Nearest Neighbor Curvature Extrapolation and Provably Generalizes on Lipschitz Functions. CoRR abs/2109.12960 (2021) - 2020
- [c5]Boris Hanin, Mihai Nica:
Finite Depth and Width Corrections to the Neural Tangent Kernel. ICLR 2020 - [i10]Boris Hanin, Yi Sun:
Data augmentation as stochastic optimization. CoRR abs/2010.11171 (2020) - [i9]Ronald A. DeVore, Boris Hanin, Guergana Petrova:
Neural Network Approximation. CoRR abs/2012.14501 (2020)
2010 – 2019
- 2019
- [c4]Boris Hanin, David Rolnick:
Complexity of Linear Regions in Deep Networks. ICML 2019: 2596-2604 - [c3]Boris Hanin, David Rolnick:
Deep ReLU Networks Have Surprisingly Few Activation Patterns. NeurIPS 2019: 359-368 - [i8]Boris Hanin, David Rolnick:
Complexity of Linear Regions in Deep Networks. CoRR abs/1901.09021 (2019) - [i7]Ingrid Daubechies, Ronald A. DeVore, Simon Foucart, Boris Hanin, Guergana Petrova:
Nonlinear Approximation and (Deep) ReLU Networks. CoRR abs/1905.02199 (2019) - [i6]Boris Hanin, David Rolnick:
Deep ReLU Networks Have Surprisingly Few Activation Patterns. CoRR abs/1906.00904 (2019) - [i5]Boris Hanin, Mihai Nica:
Finite Depth and Width Corrections to the Neural Tangent Kernel. CoRR abs/1909.05989 (2019) - 2018
- [c2]Boris Hanin, David Rolnick:
How to Start Training: The Effect of Initialization and Architecture. NeurIPS 2018: 569-579 - [c1]Boris Hanin:
Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients? NeurIPS 2018: 580-589 - [i4]Boris Hanin:
Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients? CoRR abs/1801.03744 (2018) - [i3]Boris Hanin, David Rolnick:
How to Start Training: The Effect of Initialization and Architecture. CoRR abs/1803.01719 (2018) - 2017
- [i2]Boris Hanin:
Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations. CoRR abs/1708.02691 (2017) - [i1]Boris Hanin, Mark Sellke:
Approximating Continuous Functions by ReLU Nets of Minimal Width. CoRR abs/1710.11278 (2017)
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 2024-11-25 22:46 CET 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:
