Polynomial‐time universality and limitations of deep learning

DOI10.1002/CPA.22121MaRDI QIDQ6074573FDOQ6074573

Authors: Emmanuel Abbe, Colin Sandon 

Publication date: 12 October 2023

Published in: Communications on Pure and Applied Mathematics (Search for Journal in Brave)

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Computer science (68-XX)

Cites Work

• Deep learning
• Understanding machine learning. From theory to algorithms
• Title not available (Why is that?)
• Title not available (Why is that?)
• Foundations of machine learning
• Efficient noise-tolerant learning from statistical queries
• Noise-tolerant learning, the parity problem, and the statistical query model
• Title not available (Why is that?)
• Weakly learning DNF and characterizing statistical query learning using Fourier analysis
• New lower bounds for statistical query learning
• Characterizing statistical query learning: simplified notions and proofs
• Cryptographic hardness for learning intersections of halfspaces
• Foundations of software technology and theoretical computer science. 16th conference, Hyderabad, India, December 18--20, 1996. Proceedings
• Gradient descent only converges to minimizers: non-isolated critical points and invariant regions
• Distribution-specific hardness of learning neural networks
• Statistical algorithms and a lower bound for detecting planted cliques
• On the complexity of random satisfiability problems with planted solutions
• Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimization

Cited In (1)

• Complexity of Deep Inference via Atomic Flows

This page was built for publication: Polynomial‐time universality and limitations of deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6074573)