ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2307.11947
9
2

Collaboratively Learning Linear Models with Structured Missing Data

22 July 2023
Chen Cheng
Gary Cheng
John C. Duchi
    FedML
ArXivPDFHTML
Abstract

We study the problem of collaboratively learning least squares estimates for mmm agents. Each agent observes a different subset of the features\unicodex2013\unicode{x2013}\unicodex2013e.g., containing data collected from sensors of varying resolution. Our goal is to determine how to coordinate the agents in order to produce the best estimator for each agent. We propose a distributed, semi-supervised algorithm Collab, consisting of three steps: local training, aggregation, and distribution. Our procedure does not require communicating the labeled data, making it communication efficient and useful in settings where the labeled data is inaccessible. Despite this handicap, our procedure is nearly asymptotically local minimax optimal\unicodex2013\unicode{x2013}\unicodex2013even among estimators allowed to communicate the labeled data such as imputation methods. We test our method on real and synthetic data.

View on arXiv
Comments on this paper