Learning Mixtures of Gaussians with Censored Data

Authors: Wai Ming Tai, Bryon Aragam

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We study the problem of learning mixtures of Gaussians with censored data. Statistical learning with censored data is a classical problem, with numerous practical applications, however, finitesample guarantees for even simple latent variable models such as Gaussian mixtures are missing. Formally, we are given censored data from a mixture of univariate Gaussians i=1 wi N(µi, σ2), i.e. the sample is observed only if it lies inside a set S. The goal is to learn the weights wi and the means µi. We propose an algorithm that takes only 1 εO(k) samples to estimate the weights wi and the means µi within ε error.
Researcher Affiliation Academia 1Booth School of Business, University of Chicago, Chicago, USA. Correspondence to: Wai Ming Tai <waiming.tai@chicagobooth.edu>, Bryon Aragam <bryon@chicagobooth.edu>.
Pseudocode Yes Algorithm 1 Learning mixtures of Gaussians with censored data
Open Source Code No The paper does not provide any explicit statement about releasing open-source code for their methodology or a link to a repository.
Open Datasets No The paper is theoretical and does not use or reference any datasets for training. Thus, no information about public availability of datasets is provided.
Dataset Splits No The paper is theoretical and does not involve data splitting for training, validation, or testing. Therefore, no information on dataset splits is provided.
Hardware Specification No The paper is theoretical and does not describe any experimental setup or hardware used.
Software Dependencies No The paper is theoretical and does not specify any software dependencies or versions.
Experiment Setup No The paper is theoretical and does not describe an experimental setup or hyperparameter details.