scientific article; zbMATH DE number 7626727
From MaRDI portal
Publication:5053206
Recommendations
- Convex Formulation of Overparameterized Deep Neural Networks
- scientific article; zbMATH DE number 2095982
- The global optimization geometry of shallow linear neural networks
- Breaking the curse of dimensionality with convex neural networks
- Piecewise convexity of artificial neural networks
- Provably training overparameterized neural network classifiers with non-convex constraints
- Geometry of linear convolutional networks
- Geometry of learning in multilayer perceptrons
- A geometric approach of gradient descent algorithms in linear neural networks
- Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
Cites work
- Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds
- Banach space representer theorems for neural networks and ridge splines
- Bayesian learning for neural networks
- Breaking the curse of dimensionality with convex neural networks
- Convex Analysis
- Decoding by Linear Programming
- Equivalence of minimal \(\ell _{0}\)- and \(\ell _{p }\)-norm solutions of linear equalities, inequalities and linear programs for sufficiently small \(p\)
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution
- Group invariance, stability to deformations, and complexity of deep convolutional representations
- Hardness of learning halfspaces with noise
- scientific article; zbMATH DE number 5957408 (Why is no real title available?)
- scientific article; zbMATH DE number 4061904 (Why is no real title available?)
- scientific article; zbMATH DE number 1070896 (Why is no real title available?)
- scientific article; zbMATH DE number 1179314 (Why is no real title available?)
- scientific article; zbMATH DE number 2034576 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 7626727 (Why is no real title available?)
- scientific article; zbMATH DE number 3082712 (Why is no real title available?)
- Particular formulae for the Moore--Penrose inverse of a columnwise partitioned matrix
- Probability in Banach spaces. Isoperimetry and processes
- SuperMann: A Superlinearly Convergent Algorithm for Finding Fixed Points of Nonexpansive Operators
- Wide neural networks of any depth evolve as linear models under gradient descent *
- ℓ1 Regularization in Infinite Dimensional Feature Spaces
Cited in
(9)- scientific article; zbMATH DE number 7626727 (Why is no real title available?)
- Principled deep neural network training through linear programming
- Efficient Global Optimization of Two-Layer ReLU Networks: Quadratic-Time Algorithms and Adversarial Training
- Poster: Convex Scenario Optimisation for ReLU Networks
- Kurdyka-Łojasiewicz exponent via Hadamard parametrization
- Implicit regularization towards rank minimization in ReLU networks
- Sampling theory for super-resolution with implicit neural representations
- A library of mirrors: deep neural nets in low dimensions are convex Lasso models with reflection features
- The adaptive solution of high-frequency Helmholtz equations via multi-grade deep learning
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5053206)
