Shifted composition. III: Local error framework for KL divergence
From MaRDI portal
Cites work
- An introduction to MCMC for machine learning
- Analysis and geometry of Markov diffusion operators
- Analysis of Langevin Monte Carlo via convex optimization
- Brownian motion, martingales, and stochastic calculus
- Complexity of randomized algorithms for underdamped Langevin dynamics
- Coupling and applications
- Criteria for recurrence and existence of invariant measures for multidimensional diffusions
- Harnack inequality and heat kernel estimates on manifolds with curvature unbounded below
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- High-dimensional probability. An introduction with applications in data science
- scientific article; zbMATH DE number 50401 (Why is no real title available?)
- scientific article; zbMATH DE number 3313108 (Why is no real title available?)
- scientific article; zbMATH DE number 3371284 (Why is no real title available?)
- Hypercontractivity of Hamilton-Jacobi equations.
- Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity
- Information theory. From coding to learning (to appear)
- KL convergence guarantees for score diffusion models under minimal data assumptions
- Logarithmic Sobolev inequalities on noncompact Riemannian manifolds
- Monte Carlo statistical methods
- Monte Carlo strategies in scientific computing
- On the optimal mapping of distributions
- On the privacy of noisy stochastic gradient descent for convex optimization
- Parallelized midpoint randomization for Langevin Monte Carlo
- Privacy amplification by iteration
- Rényi Divergence and Kullback-Leibler Divergence
- Sparse regression learning by aggregation and Langevin Monte-Carlo
- Stochastic numerics for mathematical physics
- Strong Data Processing Inequalities and <inline-formula> <tex-math notation="LaTeX">$\Phi $ </tex-math> </inline-formula>-Sobolev Inequalities for Discrete Channels
- Strong data-processing inequalities for channels and Bayesian networks
- The distance between two random vectors wigh given dispersion matrices
- The mirror Langevin algorithm converges with vanishing bias
- The Variational Formulation of the Fokker--Planck Equation
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
This page was built for publication: Shifted composition. III: Local error framework for KL divergence
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7446930)