Large Sample Mean-Field Stochastic Optimization
From MaRDI portal
Publication:5097396
DOI10.1137/21M1424937zbMATH Open1498.93772arXiv1906.08894MaRDI QIDQ5097396FDOQ5097396
Authors: Agostino Capponi, Huafu Liao, Lijun Bo 
Publication date: 23 August 2022
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Abstract: We study a class of sampled stochastic optimization problems, where the underlying state process has diffusive dynamics of the mean-field type. We establish the existence of optimal relaxed controls when the sample set has finite size. The core of our paper is to prove, via -convergence, that the minimizer of the finite sample relaxed problem converges to that of the limiting optimization problem. We connect the limit of the sampled objective functional to the unique solution, in the trajectory sense, of a nonlinear Fokker-Planck-Kolmogorov (FPK) equation in a random environment. We highlight the connection between the minimizers of our optimization problems and the optimal training weights of a deep residual neural network.
Full work available at URL: https://arxiv.org/abs/1906.08894
Recommendations
- Stochastic optimization for large-scale machine learning
- Variable-sample methods for stochastic optimization
- Stochastic semidefinite optimization using sampling methods
- Approximation, Randomization and Combinatorial Optimization. Algorithms and Techniques
- A stochastic quasi-Newton method for large-scale optimization
- Sampling-based approximation algorithms for multistage stochastic optimization
- scientific article; zbMATH DE number 1959636
- Adaptive sampling strategies for stochastic optimization
- Large deviations for the method of empirical means in stochastic optimization problems with continuous time observations
- Sample average approximation method for compound stochastic optimization problems
\(\Gamma\)-convergenceFokker-Planck-Kolmogorov equationrelaxed controlsdeep residual neural networksmean-field stochastic optimization
Fokker-Planck equations (35Q84) Control/observation systems governed by partial differential equations (93C20) Optimal stochastic control (93E20)
Cites Work
- Title not available (Why is that?)
- Optimal Transport
- Compact sets in the space \(L^ p(0,T;B)\)
- An introduction to \(\Gamma\)-convergence
- Title not available (Why is that?)
- Title not available (Why is that?)
- Infinite dimensional analysis. A hitchhiker's guide.
- Optimal bilinear control of nonlinear stochastic Schrödinger equations driven by linear multiplicative noise
- Compactification methods in the control of degenerate diffusions: existence of an optimal control
- OPTIMAL CONTROL OF PROBABILITY DENSITY FUNCTIONS OF STOCHASTIC PROCESSES
- Mean field limit for disordered diffusions with singular interactions
- A general characterization of the mean field limit for stochastic differential games
- Mean field games with common noise
- Optimal bilinear control of Gross-Pitaevskii equations
- Stochastic minimum principle for partially observed systems subject to continuous and jump diffusion processes and driven by relaxed controls
- On uniqueness of solutions to nonlinear Fokker-Planck-Kolmogorov equations
- On the Existence of Optimal Controls
- Mean field games via controlled martingale problems: existence of Markovian equilibria
- Probabilistic Theory of Mean Field Games with Applications I
- A mean-field optimal control formulation of deep learning
- Probabilistic Theory of Mean Field Games with Applications II
- Stable architectures for deep neural networks
- A proposal on machine learning via dynamical systems
- A mean field view of the landscape of two-layer neural networks
- The Relaxed Stochastic Maximum Principle in Singular Optimal Control of Diffusions
- Mean Field Analysis of Neural Networks: A Law of Large Numbers
- Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs
- Weak and strong error analysis for mean-field rank-based particle approximations of one-dimensional viscous scalar conservation laws
- Mean-field Markov decision processes with common noise and open-loop controls
- Mean Field Analysis of Deep Neural Networks
This page was built for publication: Large Sample Mean-Field Stochastic Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5097396)
