Related papers: Continual Invariant Risk Minimization

Continual Invariant Risk Minimization

URL: http://arxiv.org/abs/2310.13977v1
Date: Sat, 21 Oct 2023 11:44:47 GMT
Title: Continual Invariant Risk Minimization
Authors: Francesco Alesiani, Shujian Yu and Mathias Niepert
Abstract summary: Empirical risk minimization can lead to poor generalization behavior on unseen environments if the learned model does not capture invariant feature representations. Invariant risk minimization (IRM) is a recent proposal for discovering environment-invariant representations.
Score: 46.051656238770086
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Empirical risk minimization can lead to poor generalization behavior on unseen environments if the learned model does not capture invariant feature representations. Invariant risk minimization (IRM) is a recent proposal for discovering environment-invariant representations. IRM was introduced by Arjovsky et al. (2019) and extended by Ahuja et al. (2020). IRM assumes that all environments are available to the learning system at the same time. With this work, we generalize the concept of IRM to scenarios where environments are observed sequentially. We show that existing approaches, including those designed for continual learning, fail to identify the invariant features and models across sequentially presented environments. We extend IRM under a variational Bayesian and bilevel framework, creating a general approach to continual invariant risk minimization. We also describe a strategy to solve the optimization problems using a variant of the alternating direction method of multiplier (ADMM). We show empirically using multiple datasets and with multiple sequential environments that the proposed methods outperform or is competitive with prior approaches.

Related papers

Enlarging Feature Support Overlap for Domain Generalization [9.227839292188346]
Invariant risk minimization (IRM) addresses this issue by learning invariant features and minimizing the risk across different domains. We propose a novel method to enlarge feature support overlap for domain generalization. Specifically, we introduce Bayesian random data augmentation to increase sample diversity and overcome the deficiency of IRM.
arXiv Detail & Related papers (2024-07-08T09:16:42Z)
Invariant Risk Minimization Is A Total Variation Model [3.000494957386027]
Invariant risk minimization (IRM) is an arising approach to generalize invariant features to different environments in machine learning. We show that IRM is essentially a total variation based on $L2$ (TV-$ell$) of the learning risk. We propose a novel IRM framework based on the TV-$ell$ model.
arXiv Detail & Related papers (2024-05-02T15:34:14Z)
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments [55.24895403089543]
Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments. We 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.
arXiv Detail & Related papers (2021-06-18T04:39:19Z)
Robust Reconfigurable Intelligent Surfaces via Invariant Risk and Causal Representations [55.50218493466906]
In this paper, the problem of robust reconfigurable intelligent surface (RIS) system design under changes in data distributions is investigated. Using the notion of invariant risk minimization (IRM), an invariant causal representation across multiple environments is used such that the predictor is simultaneously optimal for each environment. A neural network-based solution is adopted to seek the predictor and its performance is validated via simulations against an empirical risk minimization-based design.
arXiv Detail & Related papers (2021-05-04T21:36:31Z)
Empirical or Invariant Risk Minimization? A Sample Complexity Perspective [49.43806345820883]
It is unclear when in-variant risk generalization (IRM) should be preferred over the widely-employed empirical risk minimization (ERM) framework. We find that depending on the type of data generation mechanism, the two approaches might have very different finite sample and behavior. We further investigate how different factors -- the number of environments, complexity of the model, and IRM penalty weight -- impact the sample complexity of IRM in relation to its distance from the OOD solutions.
arXiv Detail & Related papers (2020-10-30T17:55:30Z)
The Risks of Invariant Risk Minimization [52.7137956951533]
Invariant Risk Minimization is an objective based on the idea for learning deep, invariant features of data. We present the first analysis of classification under the IRM objective--as well as these recently proposed alternatives--under a fairly natural and general model. We show that IRM can fail catastrophically unless the test data are sufficiently similar to the training distribution--this is precisely the issue that it was intended to solve.
arXiv Detail & Related papers (2020-10-12T14:54:32Z)
An Empirical Study of Invariant Risk Minimization [5.412466703928342]
Invariant risk minimization is a proposed framework for learning predictors that are invariant to spurious correlations. Despite its theoretical justifications, IRM has not been extensively tested across various settings. We empirically investigate several research questions using IRMv1, which is the first practical algorithm proposed to approximately solve IRM.
arXiv Detail & Related papers (2020-04-10T12:23:29Z)
Invariant Causal Prediction for Block MDPs [106.63346115341862]
Generalization across environments is critical to the successful application of reinforcement learning algorithms to real-world challenges. We propose a method of invariant prediction to learn model-irrelevance state abstractions (MISA) that generalize to novel observations in the multi-environment setting.
arXiv Detail & Related papers (2020-03-12T21:03:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.