Provably training overparameterized neural network classifiers with non-convex constraints

DOI10.1214/22-EJS2036MaRDI QIDQ2106783zbMATH OpenFDO

Authors You-Lin Chen, Zhaoran Wang, Mladen Kolar

Publication date 19 December 2022

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2012.15274, https://projecteuclid.org/journals/electronic-journal-of-statistics/volume-16/issue-2/Provably-training-overparameterized-neural-network-classifiers-with-non-convex-constraints/10.1214/22-EJS2036.full

zbMATH Keywords

neural tangent kernelnon-convex constrained optimizationonline learning with non-convex losses

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• scientific article; zbMATH DE number 1046019 (Why is no real title available?)
• scientific article; zbMATH DE number 2023357 (Why is no real title available?)
• scientific article; zbMATH DE number 7064055 (Why is no real title available?)
• scientific article; zbMATH DE number 5060482 (Why is no real title available?)
• A dynamic near-optimal algorithm for online linear programming
• A selective overview of deep learning
• Advancing subgroup fairness via sleeping experts
• An adaptive stochastic sequential quadratic programming with differentiable exact augmented Lagrangians
• Corrigendum to: ``On the complexity of finding first-order critical points in constrained nonlinear optimization
• Fairness through awareness
• Following the leader and fast rates in online linear prediction: curved constraint sets and other regularities
• Gradient descent optimizes over-parameterized deep ReLU networks
• Non-convex optimization for machine learning
• Online Linear Programming: Dual Convergence, New Algorithms, and Regret Bounds
• Online learning and online convex optimization
• Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals
• Stochastic first-order methods for convex and nonconvex functional constrained optimization
• Stochastic model-based minimization of weakly convex functions
• Tensor Canonical Correlation Analysis With Convergence and Statistical Guarantees
• Wide neural networks of any depth evolve as linear models under gradient descent ^*

Cited in

(3)

• Provable Training of a ReLU Gate with an Iterative Non-Gradient Algorithm
• Provably Training Overparameterized Neural Network Classifiers with Non-convex Constraints
• scientific article; zbMATH DE number 7626727 (Why is no real title available?)

This page was built for publication: Provably training overparameterized neural network classifiers with non-convex constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2106783)