Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
1506.02617
Cited By
Path-SGD: Path-Normalized Optimization in Deep Neural Networks
Neural Information Processing Systems (NeurIPS), 2015
8 June 2015
Behnam Neyshabur
Ruslan Salakhutdinov
Nathan Srebro
ODL
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"Path-SGD: Path-Normalized Optimization in Deep Neural Networks"
50 / 195 papers shown
Vision Transformers provably learn spatial structure
Neural Information Processing Systems (NeurIPS), 2022
Samy Jelassi
Michael E. Sander
Yuan-Fang Li
ViT
MLT
225
102
0
13 Oct 2022
PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks
Liu Yang
Jifan Zhang
Joseph Shenouda
Dimitris Papailiopoulos
Kangwook Lee
Robert D. Nowak
354
2
0
06 Oct 2022
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
International Conference on Learning Representations (ICLR), 2022
Sungyub Kim
Si-hun Park
Kyungsu Kim
Eunho Yang
BDL
183
7
0
30 Sep 2022
Small Transformers Compute Universal Metric Embeddings
Journal of machine learning research (JMLR), 2022
Anastasis Kratsios
Valentin Debarnot
Ivan Dokmanić
317
14
0
14 Sep 2022
Quiver neural networks
I. Ganev
Robin Walters
147
4
0
26 Jul 2022
Towards understanding how momentum improves generalization in deep learning
International Conference on Machine Learning (ICML), 2022
Samy Jelassi
Yuanzhi Li
ODL
MLT
AI4CE
201
46
0
13 Jul 2022
Predicting Out-of-Domain Generalization with Neighborhood Invariance
Nathan Ng
Neha Hulkund
Dong Wang
Marzyeh Ghassemi
OOD
371
6
0
05 Jul 2022
Local Identifiability of Deep ReLU Neural Networks: the Theory
Neural Information Processing Systems (NeurIPS), 2022
Joachim Bona-Pellissier
Franccois Malgouyres
François Bachoc
FAtt
296
11
0
15 Jun 2022
Symmetry Teleportation for Accelerated Optimization
Neural Information Processing Systems (NeurIPS), 2022
B. Zhao
Nima Dehmamy
Robin Walters
Rose Yu
ODL
443
28
0
21 May 2022
Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey
Artificial Intelligence Review (Artif Intell Rev), 2022
Paul Wimmer
Jens Mehnert
Alexandru Paul Condurache
DD
336
33
0
17 May 2022
Cracking White-box DNN Watermarks via Invariant Neuron Transforms
Knowledge Discovery and Data Mining (KDD), 2022
Yifan Yan
Xudong Pan
Yining Wang
Mi Zhang
Min Yang
AAML
148
20
0
30 Apr 2022
Higher-Order Generalization Bounds: Learning Deep Probabilistic Programs via PAC-Bayes Objectives
J. Warrell
M. Gerstein
GP
183
1
0
30 Mar 2022
A Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization With Non-isolated Local Minima
Tae-Eon Ko
Xiantao Li
232
2
0
21 Mar 2022
Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning
International Conference on Machine Learning (ICML), 2022
Yang Zhao
Hao Zhang
Xiuyuan Hu
519
153
0
08 Feb 2022
Training invariances and the low-rank phenomenon: beyond linear networks
International Conference on Learning Representations (ICLR), 2022
Thien Le
Stefanie Jegelka
254
36
0
28 Jan 2022
Approximation bounds for norm constrained neural networks with applications to regression and GANs
Applied and Computational Harmonic Analysis (ACHA), 2022
Yuling Jiao
Yang Wang
Yunfei Yang
232
26
0
24 Jan 2022
Weight Expansion: A New Perspective on Dropout and Generalization
Gao Jin
Xinping Yi
Pengfei Yang
Lijun Zhang
S. Schewe
Xiaowei Huang
283
6
0
23 Jan 2022
Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
Devansh Bisla
Jing Wang
A. Choromańska
331
45
0
20 Jan 2022
Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation
Shayan Aziznejad
Joaquim Campos
M. Unser
249
12
0
12 Dec 2021
GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily
The Web Conference (WWW), 2021
Lun Du
Xiaozhou Shi
Qiang Fu
Xiaojun Ma
Hengyu Liu
Shi Han
Dongmei Zhang
496
143
0
29 Oct 2021
In Search of Probeable Generalization Measures
International Conference on Machine Learning and Applications (ICMLA), 2021
Jonathan Jaegerman
Khalil Damouni
M. M. Ankaralı
Konstantinos N. Plataniotis
158
2
0
23 Oct 2021
Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks
Tolga Ergen
Mert Pilanci
441
18
0
18 Oct 2021
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
International Conference on Learning Representations (ICLR), 2021
R. Entezari
Hanie Sedghi
O. Saukh
Behnam Neyshabur
MoMe
605
273
0
12 Oct 2021
Perturbated Gradients Updating within Unit Space for Deep Learning
Ching-Hsun Tseng
Liu Cheng
Shin-Jye Lee
Xiaojun Zeng
378
5
0
01 Oct 2021
Understanding neural networks with reproducing kernel Banach spaces
Francesca Bartolucci
Ernesto De Vito
Lorenzo Rosasco
Stefano Vigogna
278
59
0
20 Sep 2021
Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks
Rahul Parhi
Robert D. Nowak
356
43
0
18 Sep 2021
Batch Normalization Preconditioning for Neural Network Training
Susanna Lange
Kyle E. Helfrich
Qiang Ye
210
14
0
02 Aug 2021
An Embedding of ReLU Networks and an Analysis of their Identifiability
Constructive approximation (Constr. Approx.), 2021
Pierre Stock
Rémi Gribonval
283
24
0
20 Jul 2021
Universal approximation and model compression for radial neural networks
I. Ganev
Twan van Laarhoven
Robin Walters
303
10
0
06 Jul 2021
Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Xuanyu Wu
Xuhong Li
Haoyi Xiong
Xiao Zhang
Siyu Huang
Dejing Dou
116
1
0
20 Jun 2021
Solving hybrid machine learning tasks by traversing weight space geodesics
G. Raghavan
Matt Thomson
91
0
0
05 Jun 2021
What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory
SIAM Journal on Mathematics of Data Science (SIMODS), 2021
Rahul Parhi
Robert D. Nowak
MLT
412
75
0
07 May 2021
Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks
Neural Information Processing Systems (NeurIPS), 2021
Hidenori Tanaka
D. Kunin
359
39
0
06 May 2021
SGD Implicitly Regularizes Generalization Error
Daniel A. Roberts
MLT
127
17
0
10 Apr 2021
Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation
International Conference on Learning Representations (ICLR), 2021
Yang Zhao
Hao Zhang
253
8
0
17 Mar 2021
Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization
Ziquan Liu
Yufei Cui
Jia Wan
Yushun Mao
Antoni B. Chan
249
2
0
06 Feb 2021
Accelerating Training of Batch Normalization: A Manifold Perspective
Conference on Uncertainty in Artificial Intelligence (UAI), 2021
Mingyang Yi
285
3
0
08 Jan 2021
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
International Conference on Machine Learning (ICML), 2020
Bohan Wang
Qi Meng
Wei Chen
Tie-Yan Liu
281
41
0
11 Dec 2020
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
D. Kunin
Javier Sagastuy-Breña
Surya Ganguli
Daniel L. K. Yamins
Hidenori Tanaka
346
89
0
08 Dec 2020
Characterization of Excess Risk for Locally Strongly Convex Population Risk
Neural Information Processing Systems (NeurIPS), 2020
Mingyang Yi
Ruoyu Wang
Zhi-Ming Ma
340
3
0
04 Dec 2020
Neural Teleportation
M. Armenta
Thierry Judge
Nathan Painchaud
Youssef Skandarani
Carl Lemaire
Gabriel Gibeau Sanchez
Philippe Spino
Pierre-Marc Jodoin
338
20
0
02 Dec 2020
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
Neural Information Processing Systems (NeurIPS), 2020
Jack Parker-Holder
Luke Metz
Cinjon Resnick
Hengyuan Hu
Adam Lerer
Alistair Letcher
A. Peysakhovich
Aldo Pacchiano
Jakob N. Foerster
188
25
0
12 Nov 2020
An Information-Geometric Distance on the Space of Tasks
International Conference on Machine Learning (ICML), 2020
Yansong Gao
Pratik Chaudhari
204
22
0
01 Nov 2020
The power of quantum neural networks
Nature Computational Science (NCS), 2020
Amira Abbas
David Sutter
Christa Zoufal
Aurelien Lucchi
Alessio Figalli
Stefan Woerner
528
948
0
30 Oct 2020
Effective Regularization Through Loss-Function Metalearning
IEEE Congress on Evolutionary Computation (CEC), 2020
Santiago Gonzalez
Xin Qiu
Risto Miikkulainen
522
5
0
02 Oct 2020
Learning Optimal Representations with the Decodable Information Bottleneck
Neural Information Processing Systems (NeurIPS), 2020
Yann Dubois
Douwe Kiela
D. Schwab
Ramakrishna Vedantam
247
50
0
27 Sep 2020
MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search
Kengo Machida
Kuniaki Uto
Koichi Shinoda
Taiji Suzuki
150
0
0
19 Sep 2020
Extreme Memorization via Scale of Initialization
International Conference on Learning Representations (ICLR), 2020
Harsh Mehta
Ashok Cutkosky
Behnam Neyshabur
165
21
0
31 Aug 2020
Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Justin Sahs
Ryan Pyle
Aneel Damaraju
J. O. Caro
Onur Tavaslioglu
Andy Lu
Ankit B. Patel
208
20
0
04 Aug 2020
The Representation Theory of Neural Networks
M. Armenta
Pierre-Marc Jodoin
338
35
0
23 Jul 2020
Previous
1
2
3
4
Next
Page 2 of 4
