Global Optimization via Schrödinger–Föllmer Diffusion
From MaRDI portal
Publication:6057791
DOI10.1137/22m1477738zbMath1522.90120arXiv2111.00402OpenAlexW3209115427MaRDI QIDQ6057791
Lican Kang, Xiliang Lu, Yu Ling Jiao, Yin Dai, Jerry Zhijian Yang
Publication date: 26 October 2023
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2111.00402
Computational methods for problems pertaining to probability theory (60-08) Nonconvex programming, global optimization (90C26)
Cites Work
- Computational Optimal Transport: With Applications to Data Science
- Smooth minimization of non-smooth functions
- Representation formula for the entropy and functional inequalities
- A survey of the Schrödinger problem and some of its connections with optimal transport
- Poincaré and logarithmic Sobolev inequalities by decomposition of the energy landscape
- A stochastic control approach to reciprocal diffusion processes
- Log-Sobolev inequalities: different roles of Ric and Hess
- Asymptotics of the spectral gap with applications to the theory of simulated annealing
- Laplace's method revisited: Weak convergence of probability measures
- Convergence rates for annealing diffusion processes
- Accelerated information gradient flow
- Unbiased estimation using a class of diffusion processes
- Bayesian learning via neural Schrödinger-Föllmer flows
- Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity
- On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
- Stability of the logarithmic Sobolev inequality via the Föllmer process
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- Rate of convergence for ergodic continuous Markov processes: Lyapunov versus Poincaré
- Stein's lemma for elliptical random vectors
- Coupling and convergence for Hamiltonian Monte Carlo
- Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization
- Simulation and Inference for Stochastic Processes with YUIMA
- Diffusion for Global Optimization in $\mathbb{R}^n $
- A Generalization of Laplaces's Method
- [https://portal.mardi4nfdi.de/wiki/Publication:4140092 The Markov processes of Schr�dinger]
- Analysis and Geometry of Markov Diffusion Operators
- Stochastic Control Liaisons: Richard Sinkhorn Meets Gaspard Monge on a Schrödinger Bridge
- A consensus-based global optimization method for high dimensional machine learning problems
- Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler
- On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
- Stochastic Processes and Applications
- Sampling can be faster than optimization
- A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
- Asymptotic probabilities and differential equations
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
