Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
From MaRDI portal
Cited in
(48)- Asymptotic properties of one-layer artificial neural networks with sparse connectivity
- Neural network stochastic differential equation models with applications to financial data forecasting
- 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
- Gaussian random field approximation via Stein's method with applications to wide random neural networks
- Response theory identifies reaction coordinates and explains critical phenomena in noisy interacting systems
- Global contractivity for Langevin dynamics with distribution-dependent forces and uniform in time propagation of chaos
- Consensus-based optimization methods converge globally
- Phase diagram of stochastic gradient descent in high-dimensional two-layer neural networks
- Self-consistent dynamical field theory of kernel evolution in wide neural networks
- Fredholm integral equations for function approximation and the training of neural networks
- Propagation of chaos for point processes induced by particle systems with mean-field drift interaction
- Fractional interacting particle system: drift parameter estimation via Malliavin calculus
- Solutions of stationary McKean-Vlasov equation on a high-dimensional sphere and other Riemannian manifolds
- LDP for the covariance process in fully connected Gaussian neural networks
- Large deviations principle for the tagged empirical field of a general interacting gas
- Optimal sequencing depth for single-cell RNA-sequencing in Wasserstein space
- Early alignment in two-layer networks training is a two-edged sword
- Generative adversarial networks: dynamics
- Uniform-in-time propagation of chaos for mean field Langevin dynamics
- High-dimensional scaling limits and fluctuations of online least-squares SGD with smooth covariance
- Why shallow networks struggle to approximate and learn high frequencies
- Conservative SPDEs as fluctuating mean field limits of stochastic gradient descent
- Linearization of ergodic McKean SDEs and applications
- Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers
- Modulated logarithmic Sobolev inequalities and generation of chaos
- Long run convergence of discrete-time interacting particle systems of the McKean-Vlasov type
- Large deviations of one-hidden-layer neural networks
- Solving stationary nonlinear Fokker-Planck equations via sampling
- Tilting the odds at the lottery: the interplay of overparameterisation and curricula in neural networks
- Mean-field limit from general mixtures of experts to quantum neural networks
- Optimal protocols for continual learning via statistical physics and control theory
- Asymptotic generalization error in the online learning of linearized two-layer neural networks
- Convergence of drift-diffusion PDEs arising as Wasserstein gradient flows of convex functions
- Global energy minimizers for a diffusion-aggregation model on sphere
- Long-time and chaotic dynamics in microscopic systems with singular interactions
- Uniform-in-N log-Sobolev inequality for the mean-field Langevin dynamics with convex energy
- Pseudo almost automorphic solutions to delayed McKean-Vlasov integro-differential equations with Lévy noise and its optimal control
- Accelerating particle-based energetic variational inference
- Gradient is all you need? How consensus-based optimization can be interpreted as a stochastic relaxation of gradient descent
- Rearranged stochastic heat equation: ergodicity and related gradient flow on \(\mathcal{P}(\mathbb{R})\)
- Fundamental limits of overparametrized shallow neural networks for supervised learning
This page was built for publication: Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5043757)
