Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization

02/13/2020
by   Vikas K. Garg, et al.
26

Domain generalization is the problem of machine learning when the training data and the test data come from different data domains. We present a simple theoretical model of learning to generalize across domains in which there is a meta-distribution over data distributions, and those data distributions may even have different supports. In our model, the training data given to a learning algorithm consists of multiple datasets each from a single domain drawn in turn from the meta-distribution. We study this model in three different problem settings—a multi-domain Massart noise setting, a decision tree multi-dataset setting, and a feature selection setting, and find that computationally efficient, polynomial-sample domain generalization is possible in each. Experiments demonstrate that our feature selection algorithm indeed ignores spurious correlations and improves generalization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/30/2023

Robust Meta Learning for Image based tasks

A machine learning model that generalizes well should obtain low errors ...
research
08/17/2020

Zero Shot Domain Generalization

Standard supervised learning setting assumes that training data and test...
research
05/25/2023

Meta Adaptive Task Sampling for Few-Domain Generalization

To ensure the out-of-distribution (OOD) generalization performance, trad...
research
02/25/2021

An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization

A popular assumption for out-of-distribution generalization is that the ...
research
01/21/2021

Out-of-Distribution Generalization Analysis via Influence Function

The mismatch between training and target data is one major challenge for...
research
10/26/2022

Is Out-of-Distribution Detection Learnable?

Supervised learning aims to train a classifier under the assumption that...
research
08/03/2021

Generalization in Multimodal Language Learning from Simulation

Neural networks can be powerful function approximators, which are able t...

Please sign up or login with your details

Forgot password? Click here to reset