DeepAI AI Chat
Log In Sign Up

Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments

by   Yining Chen, et al.

Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments. Despite a proliferation of proposal algorithms for this task, assessing their performance, both theoretically and empirically is still very challenging. Moreover, recent approaches such as Invariant Risk Minimization (IRM) require a prohibitively large number of training environments - linear in the dimension of the spurious feature space d_s - even on simple data models like the one proposed by [Rosenfeld et al., 2021]. Under a variant of this model, we show that both ERM and IRM cannot generalize with o(d_s) environments. We then present a new algorithm based on performing iterative feature matching that is guaranteed with high probability to yield a predictor that generalizes after seeing only O(logd_s) environments.


page 1

page 2

page 3

page 4


Provable Domain Generalization via Invariant-Feature Subspace Recovery

Domain generalization asks for models trained on a set of training envir...

An Empirical Study of Invariant Risk Minimization

Invariant risk minimization (IRM; Arjovsky et al., 2019) is a recently p...

Invariant Risk Minimization Games

The standard risk minimization paradigm of machine learning is brittle w...

Does Invariant Risk Minimization Capture Invariance?

We show that the Invariant Risk Minimization (IRM) formulation of Arjovs...

Domain Extrapolation via Regret Minimization

Many real prediction tasks such as molecular property prediction require...

Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment

This work studies the generalization issue of face anti-spoofing (FAS) m...

Finding lost DG: Explaining domain generalization via model complexity

The domain generalization (DG) problem setting challenges a model traine...