Fast Convex Pruning of Deep Neural Networks

DOI10.1137/19M1246468zbMath1484.90072arXiv1806.06457OpenAlexW3008070224WikidataQ111519485 ScholiaQ111519485MaRDI QIDQ5027023

Justin Romberg, Alireza Aghasi, Afshin Abdi

Publication date: 3 February 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.06457

zbMATH Keywords

Rademacher complexitycompressed sensingdeep neural networksnetwork pruningbowling scheme

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Convex programming (90C25) Random matrices (algebraic aspects) (15B52) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items

Sensitivity-Informed Provable Pruning of Neural Networks, Deep Neural Networks Pruning via the Structured Perspective Regularization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• A tail inequality for quadratic forms of subgaussian random vectors
• Weak convergence and empirical processes. With applications to statistics
• Learning without Concentration
• Convex Recovery of a Structured Signal from Independent Random Linear Measurements
• The Generic Chaining
• Living on the edge: phase transitions in convex programs with random data
• Stable signal recovery from incomplete and inaccurate measurements
• Ridge Regression: Biased Estimation for Nonorthogonal Problems