Semi-discrete optimization through semi-discrete optimal transport: a framework for neural architecture search
From MaRDI portal
Publication:2121586
DOI10.1007/s00332-022-09780-2zbMath1486.35265arXiv2006.15221OpenAlexW3037025409MaRDI QIDQ2121586
Publication date: 4 April 2022
Published in: Journal of Nonlinear Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2006.15221
Reaction-diffusion equations (35K57) Relations of PDEs with special manifold structures (Riemannian, Finsler, etc.) (58J60) Methods of ordinary differential equations applied to PDEs (35A24)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Geodesic convexity of the relative entropy in reversible Markov chains
- Gradient flows of the entropy for finite Markov chains
- Gradient flow structure for McKean-Vlasov equations on discrete spaces
- A new transportation distance between non-negative measures, with applications to gradients flows with Dirichlet boundary conditions
- Compact sets in the space \(L^ p(0,T;B)\)
- Ricci curvature of finite Markov chains via convexity of the entropy
- Simple statistical gradient-following algorithms for connectionist reinforcement learning
- A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
- Gromov-Hausdorff limit of Wasserstein spaces on point clouds
- Nonlocal-interaction equation on graphs: gradient flow structure and continuum limit
- Traditional and accelerated gradient descent for neural architecture search
- Homogenisation of one-dimensional discrete optimal transport
- Fokker-Planck equations for a free energy functional or Markov process on a graph
- A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights
- Gromov--Hausdorff Convergence of Discrete Transportation Metrics
- A gradient structure for reaction–diffusion systems and for energy-drift-diffusion systems
- The Variational Formulation of the Fokker--Planck Equation
- Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler
- Scaling Limits of Discrete Optimal Transport
- Optimal Transport
This page was built for publication: Semi-discrete optimization through semi-discrete optimal transport: a framework for neural architecture search
