Near-Optimality of Contrastive Divergence Algorithms

Authors: Pierre Glaser, Kevin Han Huang, Arthur Gretton

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We perform a non-asymptotic analysis of the contrastive divergence (CD) algorithm, a training method for unnormalized models. While prior work has established that (for exponential family distributions) the CD iterates asymptotically converge at an O(n 1/3) rate to the true parameter of the data distribution, we show, under some regularity assumptions, that CD can achieve the parametric rate O(n 1/2).
Researcher Affiliation Academia Pierre Glaser Kevin Han Huang Arthur Gretton Gatsby Computational Neuroscience Unit, University College London pierreglaser@gmail.com, han.huang.20@ucl.ac.uk, arthur.gretton@gmail.com
Pseudocode Yes Algorithm 1 Online CD
Open Source Code No The paper does not include experiments, and thus no code or data.
Open Datasets No The paper is a theoretical analysis and does not involve empirical studies with specific datasets for training or evaluation.
Dataset Splits No The paper is a theoretical analysis and does not involve empirical studies with specific dataset splits for validation.
Hardware Specification No The paper is a theoretical analysis and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is a theoretical analysis and does not list specific software dependencies with version numbers for experimental replication.
Experiment Setup No The paper is a theoretical analysis and does not describe an experimental setup, hyperparameters, or system-level training settings.