• Bio
  • Talks
  • Papers
  • Projects
  • Publications
    • Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities
    • Momentum Particle Maximum Likelihood
    • The divide-and-conquer sequential Monte Carlo algorithm: theoretical properties and limit theorems
    • Particle algorithms for maximum likelihood training of latent variable models
    • Product-form estimators: exploiting independence to scale up Monte Carlo
    • Approximations of Countably Infinite Linear Programs over Bounded Measure Spaces
    • Stationary Distributions of Continuous-Time Markov Chains: A Review of Theory and Truncation-Based Approximations
    • Markov chains revisited
    • Bounding the stationary distributions of the chemical master equation via mathematical programming
    • Diffusion limit for the random walk Metropolis algorithm out of stationarity
    • The exit time finite state projection scheme: bounding exit distributions and occupation measures of continuous-time Markov chains
    • Non-stationary phase of the MALA algorithm
    • Deterministic approximation schemes with computable errors for the distributions of Markov chains
    • Bounding Stationary Averages of Polynomial Diffusions via Semidefinite Programming
    • Model Reduction of Genetic-Metabolic Networks via Time Scale Separation
  • Experience
  • Recent & Upcoming Talks
    • Particle algorithms for maximum likelihood training of latent variable models
    • Otto calculus and deep fakes
    • Product-form estimators: exploiting independence to scale up Monte Carlo
  • Blog
  • Teaching

Particle algorithms for maximum likelihood training of latent variable models

Apr 26, 2023 · 0 min read
Video Article
Abstract
A brief overview of the paper by the same name.
Date
Apr 26, 2023 2:00 PM
Last updated on Apr 26, 2023
Juan Kuntz
Authors
Juan Kuntz
Senior Research Engineer
Otto calculus and deep fakes Apr 5, 2023 →

© 2024 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.