DeepAI AI Chat
Log In Sign Up

Pareto Invariant Risk Minimization

06/15/2022
by   Yongqiang Chen, et al.
The Chinese University of Hong Kong
5

Despite the success of invariant risk minimization (IRM) in tackling the Out-of-Distribution generalization problem, IRM can compromise the optimality when applied in practice. The practical variants of IRM, e.g., IRMv1, have been shown to have significant gaps with IRM and thus could fail to capture the invariance even in simple problems. Moreover, the optimization procedure in IRMv1 involves two intrinsically conflicting objectives, and often requires careful tuning for the objective weights. To remedy the above issues, we reformulate IRM as a multi-objective optimization problem, and propose a new optimization scheme for IRM, called PAreto Invariant Risk Minimization (PAIR). PAIR can adaptively adjust the optimization direction under the objective conflicts. Furthermore, we show PAIR can empower the practical IRM variants to overcome the barriers with the original IRM when provided with proper guidance. We conduct experiments with ColoredMNIST to confirm our theory and the effectiveness of PAIR.

READ FULL TEXT

page 2

page 3

01/04/2021

Does Invariant Risk Minimization Capture Invariance?

We show that the Invariant Risk Minimization (IRM) formulation of Arjovs...
07/05/2019

Invariant Risk Minimization

We introduce Invariant Risk Minimization (IRM), a learning paradigm to e...
10/24/2021

Kernelized Heterogeneous Risk Minimization

The ability to generalize under distributional shifts is essential to re...
03/04/2023

What Is Missing in IRM Training and Evaluation? Challenges and Solutions

Invariant risk minimization (IRM) has received increasing attention as a...
01/28/2023

Learning Optimal Features via Partial Invariance

Learning models that are robust to test-time distribution shifts is a ke...
01/25/2022

Conditional entropy minimization principle for learning domain invariant representation features

Invariance principle-based methods, for example, Invariant Risk Minimiza...
10/13/2021

A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark

In this paper, the authors investigate the Deep Sea Treasure (DST) probl...