Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
From MaRDI portal
Publication:5043757
DOI10.1002/CPA.22074OpenAlexW4286717651MaRDI QIDQ5043757
Grant Rotskoff, Eric Vanden-Eijnden
Publication date: 6 October 2022
Published in: Communications on Pure and Applied Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1805.00915
Related Items (10)
Two-Layer Neural Networks with Values in a Banach Space ⋮ Adaptive and Implicit Regularization for Matrix Completion ⋮ Global-in-time mean-field convergence for singular Riesz-type diffusive flows ⋮ Online parameter estimation for the McKean-Vlasov stochastic differential equation ⋮ McKean-Vlasov equations involving hitting times: blow-ups and global solvability ⋮ Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics ⋮ A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling ⋮ Reversible coalescing-fragmentating Wasserstein dynamics on the real line ⋮ Neural network stochastic differential equation models with applications to financial data forecasting ⋮ Asymptotic properties of one-layer artificial neural networks with sparse connectivity
This page was built for publication: Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
