Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales

Terms and Conditions

Twitter GitHub LinkedIn Bluesky Youtube

© 2026 ResearchTrend.AI, All rights reserved.

Home
Papers
2012.03224
Cited By

Benefit of deep learning with non-convex noisy gradient descent:
Provable excess risk bound and superiority to kernel methods

Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods

International Conference on Learning Representations (ICLR), 2020

6 December 2020

ArXiv (abs)PDF HTML

Papers citing "Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods"

11 / 11 papers shown

Operator Learning Using Random Features: A Tool for Scientific Computing

Operator Learning Using Random Features: A Tool for Scientific ComputingSIAM Review (SIAM Rev.), 2024

Nicholas H. Nelsen

Andrew M. Stuart

314

26

0

12 Aug 2024

SGD Finds then Tunes Features in Two-Layer Neural Networks with
near-Optimal Sample Complexity: A Case Study in the XOR problem

SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problemInternational Conference on Learning Representations (ICLR), 2023

Margalit Glasgow

405

24

0

26 Sep 2023

SGD learning on neural networks: leap complexity and saddle-to-saddle
dynamics

SGD learning on neural networks: leap complexity and saddle-to-saddle dynamicsAnnual Conference Computational Learning Theory (COLT), 2023

Enric Boix-Adserà

Theodor Misiakiewicz

370

126

0

21 Feb 2023

Stability and Generalization Analysis of Gradient Methods for Shallow
Neural Networks

Stability and Generalization Analysis of Gradient Methods for Shallow Neural NetworksNeural Information Processing Systems (NeurIPS), 2022

320

26

0

19 Sep 2022

Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student
Settings and its Superiority to Kernel Methods

Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel MethodsInternational Conference on Learning Representations (ICLR), 2022

279

9

0

30 May 2022

High-dimensional Asymptotics of Feature Learning: How One Gradient Step
Improves the Representation

High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the RepresentationNeural Information Processing Systems (NeurIPS), 2022

Jimmy Ba

Murat A. Erdogdu

287

140

0

03 May 2022

Stability & Generalisation of Gradient Descent for Shallow Neural
Networks without the Neural Tangent Kernel

Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent KernelNeural Information Processing Systems (NeurIPS), 2021

Dominic Richards

Ilja Kuzborskij

207

37

0

27 Jul 2021

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks
in Teacher-Student Setting

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student SettingInternational Conference on Machine Learning (ICML), 2021

325

16

0

11 Jun 2021

Classifying high-dimensional Gaussian mixtures: Where kernel methods
fail and neural networks succeed

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeedInternational Conference on Machine Learning (ICML), 2021

Maria Refinetti

Sebastian Goldt

Florent Krzakala

Lenka Zdeborová

265

83

0

23 Feb 2021

Dimension-free convergence rates for gradient Langevin dynamics in RKHS

Dimension-free convergence rates for gradient Langevin dynamics in RKHSAnnual Conference Computational Learning Theory (COLT), 2020

Mathurin Massias

382

12

0

29 Feb 2020

Deep learning is adaptive to intrinsic dimensionality of model
smoothness in anisotropic Besov space

Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov spaceNeural Information Processing Systems (NeurIPS), 2019

Atsushi Nitanda

402

74

0

28 Oct 2019

Page 1 of 1