On Learning Markov Chains

Authors: Yi Hao, Alon Orlitsky, Venkatadheeraj Pichapati

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We augment the theory with experiments that demonstrate the efficacy of our proposed estimators and validate the functional form of the derived bounds.
Researcher Affiliation Academia Yi HAO Dept. of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92093 yih179@ucsd.edu Alon Orlitsky Dept. of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92093 alon@ucsd.edu Venkatadheeraj Pichapati Dept. of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92093 dheerajpv7@ucsd.edu
Pseudocode No The paper provides mathematical definitions of estimators but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about the availability of source code or links to a code repository.
Open Datasets No The paper describes a process for generating synthetic data for experiments (e.g., 'drawn from the k-Dirichlet(1) distribution', 'construct a transition matrix M'), but does not provide concrete access information (link, DOI, formal citation) to a publicly available or open dataset.
Dataset Splits No The paper describes parameters for data generation (e.g., '10,000 <= n <= 100,000'), but it does not specify explicit training, validation, or test dataset splits.
Hardware Specification No The paper does not provide any specific details regarding the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide any specific software dependencies or versions (e.g., programming languages, libraries, frameworks) used for the experiments.
Experiment Setup Yes For the first three figures, k = 6, δ = 0.05, and 10, 000 n 100, 000. For the last figure, δ = 0.01, n = 100, 000, and 4 k 36. In all the experiments, the initial distribution µ of the Markov chain is drawn from the k-Dirichlet(1) distribution. For the transition matrix M, we first construct a transition matrix M where each row is drawn independently from the k-Dirichlet(1) distribution. To ensure that each element of M is at least δ, let Jk represent the k k all-ones matrix, and set M = M (1 kδ) + δJk. We generate a new Markov chain for each curve in the plots. And each data point on the curve shows the average loss of 100 independent restarts of the same Markov chain.