Poly-time universality and limitations of deep learning

7 January 2020

Papers citing "Poly-time universality and limitations of deep learning"

17 / 17 papers shown

Title
From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency Kaiyue Wen Huaqing Zhang Hongzhou Lin Jingzhao Zhang MoE LRM 175 7 0 07 Oct 2024
How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD Pierfrancesco Beneventano Andrea Pinto Tomaso A. Poggio MLT 56 1 0 17 Jun 2024
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression Adam Block Dylan J. Foster Akshay Krishnamurthy Max Simchowitz Cyril Zhang 75 7 0 17 Oct 2023
Practically Solving LPN in High Noise Regimes Faster Using Neural Networks Haozhe Jiang Kaiyue Wen Yi-Long Chen 52 0 0 14 Mar 2023
On the non-universality of deep learning: quantifying the cost of symmetry Emmanuel Abbe Enric Boix-Adserà FedML MLT 80 19 0 05 Aug 2022
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit Boaz Barak Benjamin L. Edelman Surbhi Goel Sham Kakade Eran Malach Cyril Zhang 114 133 0 18 Jul 2022
$Intrinsic dimensionality and generalization properties of the $\mathcal{R}$-norm inductive bias$ Intrinsic dimensionality and generalization properties of the $\mathcal{R}$ -norm inductive bias Navid Ardeshir Daniel J. Hsu Clayton Sanford CML AI4CE 113 6 0 10 Jun 2022
The Theoretical Expressiveness of Maxpooling Kyle Matoba Nikolaos Dimitriadis Franccois Fleuret FAtt 52 3 0 02 Mar 2022
An initial alignment between neural network and target is needed for gradient descent to learn Emmanuel Abbe Elisabetta Cornacchia Jan Hązła Christopher Marquis 117 16 0 25 Feb 2022
The effective noise of Stochastic Gradient Descent Francesca Mignacco Pierfrancesco Urbani 69 39 0 20 Dec 2021
Regularization by Misclassification in ReLU Neural Networks Elisabetta Cornacchia Jan Hązła Ido Nachum Amir Yehudayoff NoLa 59 2 0 03 Nov 2021
On the Cryptographic Hardness of Learning Single Periodic Neurons M. Song Ilias Zadik Joan Bruna AAML 68 28 0 20 Jun 2021
Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem Francesca Mignacco Pierfrancesco Urbani Lenka Zdeborová 85 36 0 08 Mar 2021
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels Eran Malach Pritish Kamath Emmanuel Abbe Nathan Srebro 80 39 0 01 Mar 2021
The Connection Between Approximation, Depth Separation and Learnability in Neural Networks Eran Malach Gilad Yehudai Shai Shalev-Shwartz Ohad Shamir 87 20 0 31 Jan 2021
Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't E. Weinan Chao Ma Stephan Wojtowytsch Lei Wu AI4CE 125 134 0 22 Sep 2020
Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent Surbhi Goel Aravind Gollakota Zhihan Jin Sushrut Karmalkar Adam R. Klivans MLT ODL 75 72 0 22 Jun 2020