Analysis of kinetic models for label switching and stochastic gradient descent
DOI10.3934/krm.2023005zbMath1524.35499arXiv2207.00389OpenAlexW4319734229MaRDI QIDQ6106920
Publication date: 3 July 2023
Published in: Kinetic and Related Models (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2207.00389
machine learningstochastic gradient descentlabel switchingintegro-partial differential equationsrun-and-tumble particles
Artificial neural networks and deep learning (68T07) Integro-partial differential equations (45K05) Existence problems for PDEs: global existence, local existence, non-existence (35A01) Integro-partial differential equations (35R09) Uniqueness problems for PDEs: global uniqueness, local uniqueness, non-uniqueness (35A02) Transport equations (35Q49)
Related Items (1)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Functional analysis, Sobolev spaces and partial differential equations
- Measure solutions for some models in population dynamics
- Uniform-in-time weak error analysis for stochastic gradient descent algorithms via diffusion approximation
- Analysis of stochastic gradient descent in continuous time
- Boltzmann-type equations for multi-agent systems with label switching
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- Transport distances for PDEs: the coupling method
- Probability and Stochastics
- Probability with Martingales
- Hydrodynamic Limit For An Active Exclusion Process
- Large time behaviors of upwind schemes and $B$-schemes for Fokker-Planck equations on $\mathbb {R}$ by jump processes
- Stochastic gradient descent with noise of machine learning type. I: Discrete time analysis
This page was built for publication: Analysis of kinetic models for label switching and stochastic gradient descent