mlsanityData to 7 Oct 2026

Spectral Experts for Estimating Mixtures of Linear Regressions

arXiv 1306.3729 ↗First posted 17 Jun 2013cs.LG stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

Discriminative latent-variable models are typically learned using EM or gradient-based optimization, which suffer from local optima. In this paper, we develop a new computationally efficient and provably consistent estimator for a mixture of linear regressions, a simple instance of a discriminative latent-variable model. Our approach relies on a low-rank linear regression to recover a symmetric tensor, which can be factorized into the parameters using a tensor power method. We prove rates of convergence for our estimator and provide an empirical evaluation illustrating its strengths relative to local optimization (EM).

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jun 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 3; 2022: 6; 2023: 7; 2024: 2; 2025: 1; 2026: 2.

22 papers.

Sort:

By area:

  1. 2022Towards Understanding Mixture of Experts in Deep Learningcited by 52
  2. 2018Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithmscited by 13
  3. 2022On Learning Mixture of Linear Regressions in the Non-Realizable Settingcited by 10
  4. 2021A Wasserstein Minimax Framework for Mixed Linear Regressioncited by 7
  5. 2023Statistical-Computational Tradeoffs in Mixed Sparse Linear Regressioncited by 7
  6. 2021Support Recovery of Sparse Signals from a Mixture of Linear Measurementscited by 6
  7. 2022Efficient List-Decodable Regression using Batchescited by 5
  8. 2022Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxationcited by 4
  9. 2022Tight Bounds on the Hardness of Learning Simple Nonparametric Mixturescited by 3
  10. 2023Imbalanced Mixed Linear Regressioncited by 3
  11. 2023Mixed Regression via Approximate Message Passingcited by 3
  12. 2023Linear Regression using Heterogeneous Data Batchescited by 3
10 more
  1. 2022Support Recovery in Mixture Models with Sparse Parameterscited by 2
  2. 2025Learning and Generalization with Mixture Datacited by 2
  3. 2021Efficient Algorithms for Estimating the Parameters of Mixed Linear Regression Modelscited by 1
  4. 2023Sharp analysis of EM for learning mixtures of pairwise differencescited by 1
  5. 2023Global Convergence of Online Identification for Mixed Linear Regressioncited by 1
  6. 2024Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithmscited by 1
  7. 2024In-context Learning for Mixture of Linear Regressions: Existence, Generalization and Training Dynamicscited by 1
  8. 2023On the robust learning mixtures of linear regressionscited by 0
  9. 2026Expectation Maximization (EM) Converges for General Agnostic Mixturescited by 0
  10. 2026Robust Subgroup Analysis for Heterogeneous Censored Datacited by 0