Accelerated Flow for Probability Distributions

Authors: Amirhossein Taghvaei, Prashant Mehta

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

Reproducibility Variable Result LLM Response
Research Type Experimental The algorithm is numerically illustrated and compared with the MCMC and Hamiltonian MCMC algorithms. The numerical algorithm along with the results of numerical experiments appear in Sec. 4.
Researcher Affiliation Academia 1Department of Mechanical Science and Engineering, Coordinated Science Laboratory, University of Illinois at Urbana Champaign, Urbana, IL, USA. Correspondence to: Amirhossein Taghvaei <taghvae2@illinois.edu>.
Pseudocode Yes Algorithm 1 Interacting particle implementation of the accelerated gradient flow
Open Source Code No The paper does not provide any statements about releasing open-source code or links to a code repository.
Open Datasets No The paper uses synthetic Gaussian and non-Gaussian examples, defining initial and target distributions. It does not mention using or providing access to any publicly available or open datasets for training.
Dataset Splits No The paper does not provide specific training/validation/test dataset splits. It describes simulations for theoretical models rather than experiments on partitioned datasets.
Hardware Specification No The paper does not provide any specific hardware details such as GPU/CPU models, processors, or memory used for running the experiments.
Software Dependencies No The paper does not provide specific version numbers for any software components, libraries, or solvers used in the implementation.
Experiment Setup Yes For this simulation, the numerical parameters are as follows: N = 100, φ0(x) = 0.5(x 2), t0 = 1, t = 0.1, p = 2,C = 0.625, and K = 400. The numerical parameters are same as in the Example 4.1.