Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization

Authors: Than Huy Nguyen, Umut Simsekli, Gael Richard

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this study, we analyze the non-asymptotic behavior of FLMC for nonconvex optimization and prove finite-time bounds for its expected suboptimality. Our results show that the weak-error of FLMC increases faster than LMC, which suggests using smaller step-sizes in FLMC.
Researcher Affiliation Academia 1LTCI, T el ecom Paris Tech, Universit e Paris-Saclay, 75013, Paris, France.
Pseudocode No The paper describes algorithms using mathematical equations (e.g., Equation 2 for ULA, Equation 3 for FLA) and iterative schemes, but it does not provide any explicitly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code No The paper does not provide any statements about releasing open-source code for the described methodology, nor does it include links to a code repository.
Open Datasets No The paper is theoretical and focuses on mathematical analysis of algorithms. It does not describe any experimental training on datasets, nor does it provide access information for any datasets used by the authors.
Dataset Splits No The paper is theoretical and does not describe experimental setups with dataset splits. It does not provide any specific information about training, validation, or test splits.
Hardware Specification No The paper is theoretical and does not describe conducting experiments that would require specific hardware. No hardware specifications (e.g., GPU, CPU models, or memory) are mentioned.
Software Dependencies No The paper is theoretical and does not describe conducting experiments that would require specific software dependencies. No software names with version numbers are provided.
Experiment Setup No The paper is theoretical and focuses on mathematical analysis. It defines parameters within the algorithms (e.g., step-size η, inverse temperature β) for theoretical discussion, but it does not describe an experimental setup with hyperparameter values, training schedules, or system-level settings for actual experiments.