3 papers
stat.ME2024
Mining Invariance from Nonlinear Multi-Environment Data: Binary Classification
Austin Goddard, Kang Du, Yu Xiang
Making predictions in an unseen environment given data from multiple training environments is a challenging task. We approach this problem from an invariance perspective, focusing…
cs.LG2024
Causal Inference from Slowly Varying Nonstationary Processes
Kang Du, Yu Xiang
Causal inference from observational data following the restricted structural causal models (SCM) framework hinges largely on the asymmetry between cause and effect from the data ge…
stat.ML2024
Low-Rank Approximation of Structural Redundancy for Self-Supervised Learning
Kang Du, Yu Xiang
We study the data-generating mechanism for reconstructive SSL to shed light on its effectiveness. With an infinite amount of labeled samples, we provide a sufficient and necessary…