SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.16360 · 2023

Mean-field underdamped Langevin dynamics and its spacetime discretization

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
qiangfu09/nula canonical 1 of 2
FunctionStatusWhere it lives
trainloss Ran qiangfu09/nula/EM-UNLA.py
pointer only (licence: NONE) · get_code("6d6ec34bbcaed71e")
Gaussian_func Not yet run qiangfu09/nula/EM-UNLA.py
pointer only (licence: NONE) · get_code("d857868653e8c090")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures. Examples of problems with this formulation include training mean-field neural networks, maximum mean discrepancy minimization and kernel Stein discrepancy minimization. Our algorithm is based on a novel spacetime discretization of the mean-field underdamped Langevin dynamics, for which we provide a new, fast mixing guarantee. In addition, we demonstrate that our algorithm converges globally in total variation distance, bridging the theoretical gap between the dynamics and its practical implementation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2312.16360")
get_code_for_paper("2312.16360")
have("2312.16360")

Connect an agent — have() is free.