Arithmetic circuits, structured matrices and (not so) deep learning

DOI10.1007/s00224-022-10112-warXiv2206.12490OpenAlexW4313335199MaRDI QIDQ6109070

Atri Rudra

Publication date: 26 July 2023

Published in: Theory of Computing Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2206.12490

zbMATH Keywords

neural networkspolynomial transformslinear arithmetic circuit complexity

Mathematics Subject Classification ID

Numerical linear algebra (65Fxx) Theory of computing (68Qxx) Basic linear algebra (15Axx)

Cites Work

• Displacement ranks of matrices and linear equations
• The complexity of partial derivatives
• Robust principal component analysis?
• Complexity Lower Bounds using Linear Algebra
• Displacement Structure: Theory and Applications
• Neural Network Learning
• Probabilistic rank and matrix rigidity
• Why Are Big Data Matrices Approximately Low Rank?
• Butterfly Factorization
• An Algorithm for the Machine Calculation of Complex Fourier Series
• Optimal Rearrangeable Multistage Connecting Networks
• Fourier and Circulant Matrices are Not Rigid
• Kronecker products, low-depth circuits, and matrix rigidity
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Arithmetic circuits, structured matrices and (not so) deep learning