Statistical Efficiency of Score Matching: The View from Isoperimetry

Authors: Frederic Koehler, Alexander Heckett, Andrej Risteski

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In Section 7, we perform several simulations which illustrate the close connection between isoperimetry and the performance of score matching. We give examples both when fitting the parameters of an exponential family and when the score function is fit using a neural network.
Researcher Affiliation Academia Frederic Koehler Stanford University fkoehler@stanford.edu Alexander Heckett Carnegie Mellon University aheckett@andrew.cmu.edu Andrej Risteski Carnegie Mellon University aristesk@andrew.cmu.edu
Pseudocode No The paper does not contain any sections or blocks labeled 'Pseudocode' or 'Algorithm'.
Open Source Code No The paper does not provide an explicit statement about the release of its own source code, nor does it provide a link to a code repository.
Open Datasets No The paper discusses synthetic or generative distributions (e.g., 'a bimodal distribution', 'a mixture of Gaussians') for simulations, but does not provide concrete access information (link, DOI, repository, or formal citation with authors/year) for a publicly available or open dataset.
Dataset Splits No The paper refers to 'training data' and 'finite number of samples n' but does not provide specific details on dataset splits (percentages, counts, or references to standard splits) for training, validation, or testing.
Hardware Specification No The paper does not provide specific details regarding the hardware (e.g., CPU, GPU models, memory, or cloud instances) used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names with versions) needed to replicate the experiments.
Experiment Setup Yes Model details: both models illustrated in the figure have 2048 tanh units and are trained via SGD on fresh samples for 300000 steps.