Unveiling Invariant and Transferable Latent Factors Across Heterogeneous Environments via ATLAS
Yihong Gu, Katherine Liao, Tianxi Cai
math.ST, cs.LG, stat.ME, stat.ML
Submitted: 2026-07-20
Comments: 47 pages, 3 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Invariant Risk Minimization
- Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration
- When can weak latent factors be statistically inferred?
- Fundamental Computational Limits in Pursuing Invariant Causal Prediction and Invariance-Guided Regularization
- TransPCA for Large-dimensional Factor Analysis with Weak Factors: Power Enhancement via Knowledge Transfer
- Revisiting Asymptotic Theory for Principal Component Estimators of Approximate Factor Models
- Nonlinear multi-study sparse factor analysis
- Anchor PCA
- StablePCA: Distributionally Robust Learning of Shared Representations from Multi-Source Data
- The Causal Structure of Domain Invariant Supervised Representation Learning
- Adversarial Drift-Aware Predictive Transfer: Toward Durable Clinical AI
- Estimating shared subspace with AJIVE: the power and limitation of multiple data matrices
Related papers
- Conformal Prediction for Dyadic Regression Under Complex Missingness
- Bentkus-type asymptotic e-values
- High-Dimensional Asymptotics of Differentially Private PCA
- KL Convergence Guarantees for Score diffusion models under minimal data assumptions
- Geometric bias in eigenspace perturbation under random heterogeneous noise
- On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models