Propagation of chaos: a review of models, methods and applications. I. Models and methods
LP Chaintron, A Diez - arXiv preprint arXiv:2203.00446, 2022 - arxiv.org
The notion of propagation of chaos for large systems of interacting particles originates in
statistical physics and has recently become a central notion in many areas of applied …
statistical physics and has recently become a central notion in many areas of applied …
Propagation of chaos: a review of models, methods and applications. II. Applications
LP Chaintron, A Diez - arXiv preprint arXiv:2106.14812, 2021 - arxiv.org
The notion of propagation of chaos for large systems of interacting particles originates in
statistical physics and has recently become a central notion in many areas of applied …
statistical physics and has recently become a central notion in many areas of applied …
Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
A Durmus, E Moulines - 2017 - projecteuclid.org
In this paper, we study a method to sample from a target distribution π over R^d having a
positive density with respect to the Lebesgue measure, known up to a normalisation factor …
positive density with respect to the Lebesgue measure, known up to a normalisation factor …
[图书][B] Fokker–Planck–Kolmogorov Equations
This book gives an exposition of the principal concepts and results related to second order
elliptic and parabolic equations for measures, the main examples of which are Fokker …
elliptic and parabolic equations for measures, the main examples of which are Fokker …
High-dimensional Bayesian inference via the unadjusted Langevin algorithm
A Durmus, E Moulines - 2019 - projecteuclid.org
High-dimensional Bayesian inference via the unadjusted Langevin algorithm Page 1
Bernoulli 25(4A), 2019, 2854–2882 https://doi.org/10.3150/18-BEJ1073 High-dimensional …
Bernoulli 25(4A), 2019, 2854–2882 https://doi.org/10.3150/18-BEJ1073 High-dimensional …
Analysis of Langevin Monte Carlo via convex optimization
In this paper, we provide new insights on the Unadjusted Langevin Algorithm. We show that
this method can be formulated as the first order optimization algorithm for an objective …
this method can be formulated as the first order optimization algorithm for an objective …
Score-based generative modeling secretly minimizes the wasserstein distance
Score-based generative models are shown to achieve remarkable empirical performances
in various applications such as image generation and audio synthesis. However, a …
in various applications such as image generation and audio synthesis. However, a …
[图书][B] Representations of algebraic groups
JC Jantzen - 2003 - books.google.com
Now back in print by the AMS, this is a significantly revised edition of a book originally
published in 1987 by Academic Press. This book gives the reader an introduction to the …
published in 1987 by Academic Press. This book gives the reader an introduction to the …
Measuring sample quality with Stein's method
To improve the efficiency of Monte Carlo estimation, practitioners are turning to biased
Markov chain Monte Carlo procedures that trade off asymptotic exactness for computational …
Markov chain Monte Carlo procedures that trade off asymptotic exactness for computational …
Reflection couplings and contraction rates for diffusions
A Eberle - Probability theory and related fields, 2016 - Springer
We consider contractivity for diffusion semigroups wrt Kantorovich (L^ 1 L 1 Wasserstein)
distances based on appropriately chosen concave functions. These distances are …
distances based on appropriately chosen concave functions. These distances are …