Research map / Learning theory and algorithms / Sample complexity
Linear Regression Under Misalignment: Algorithms and Theoretical Results
Sanjivni Rana, Suraj Shetiya, Senjuti Basu Roy, Gautam Das
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies linear regression when feature-response correspondence is unknown (misaligned data), proposing algorithms and theoretical results for two related computationally distinct problems.
Problem
Linear regression is difficult when the correspondence between d-dimensional feature vectors and responses is unknown, as arises from anonymization, data fragmentation, or multi-source aggregation.
Approach
Studies two related but computationally distinct misalignment regression problems and gives algorithms with theoretical guarantees for them; the abstract is truncated so the specific method is not stated.
Closest papers by meaning
- Generalized Shuffled Linear Regression (ICCV 2021 · similarity 0.88)
- Two-Stage Approach to Multivariate Linear Regression with Sparsely Mismatched Data (JMLR 2020 · similarity 0.86)
- Learning with Exact Invariances in Polynomial Time (ICML 2025 · similarity 0.85)
- Linear Regression using Heterogeneous Data Batches (NeurIPS 2024 · similarity 0.85)
- Improved Scaling Laws in Linear Regression via Data Reuse (NeurIPS 2025 · similarity 0.84)
- Test-time Adaptation for Regression by Subspace Alignment (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
