paper-with-me

홈 › Papers

Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms

2024-06-03 · Avishek Ghosh, Arya Mazumdar

Mixed linear regression is a well-studied problem in parametric statistics and machine learning. Given a set of samples, tuples of covariates and labels, the task of mixed linear regression is to find a small list of linear relationships that best fit the samples. Usually it is assumed that the label is generated stochastically by randomly selecting one of two or more linear functions, applying this chosen function to the covariates, and potentially introducing noise to the result. In that situation, the objective is to estimate the ground-truth linear functions up to some parameter error. The popular expectation maximization (EM) and alternating minimization (AM) algorithms have been previously analyzed for this. In this paper, we consider the more general problem of agnostic learning of mixed linear regression from samples, without such generative models. In particular, we show that the AM and EM algorithms, under standard conditions of separability and good initialization, lead to agnostic learning in mixed linear regression by converging to the population loss minimizers, for suitably defined loss functions. In some sense, this shows the strength of AM and EM algorithms that converges to ``optimal solutions'' even in the absence of realizable generative models.

📄 PDF Abstract BibTeX arXiv:2406.01149

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
AM 설명 없음
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Alternating Minimization Converges Super-Linearly for Mixed Linear Regression

2020-04-23 · Avishek Ghosh, Kannan Ramchandran

We address the problem of solving mixed random linear equations. We have unlabeled observations coming from multiple linear regressions, and each observation corresponds to exactly one of the regression models. The goal …

regression

Expectation Maximization (EM) Converges for General Agnostic Mixtures

2026-04-07 · Avishek Ghosh arxiv

Mixture of linear regression is well studied in statistics and machine learning, where the data points are generated probabilistically using $k$ linear models. Algorithms like Expectation Maximization (EM) may be used to…

Support Recovery of Sparse Signals from a Mixture of Linear Measurements

2021-06-10 · NeurIPS 2021 12 · Venkata Gandikota, Arya Mazumdar, Soumyabrata Pal

Recovery of support of a sparse vector from simple measurements is a widely-studied problem, considered under the frameworks of compressed sensing, 1-bit compressed sensing, and more general single index models. We consi…

compressed sensing

Recovery of Sparse Signals from a Mixture of Linear Samples

2020-06-29 · ICML 2020 1 · Arya Mazumdar, Soumyabrata Pal

Mixture of linear regressions is a popular learning theoretic model that is used widely to represent heterogeneous data. In the simplest form, this model assumes that the labels are generated from either of two different…

compressed sensingExperimental Design

On Learning Mixture of Linear Regressions in the Non-Realizable Setting

2022-05-26 · Avishek Ghosh, Arya Mazumdar, Soumyabrata Pal, Rajat Sen

While mixture of linear regressions (MLR) is a well-studied topic, prior works usually do not analyze such models for prediction error. In fact, {\em prediction} and {\em loss} are not well-defined in the context of mixt…

Prediction