paper-with-me

홈 › Papers

Does Invariant Risk Minimization Capture Invariance?

2021-01-04 · Pritish Kamath, Akilesh Tangella, Danica J. Sutherland, Nathan Srebro

We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture "natural" invariances, at least when used in its practical "linear" form, and even on very simple problems which directly follow the motivating examples for IRM. This can lead to worse generalization on new environments, even when compared to unconstrained ERM. The issue stems from a significant gap between the linear variant (as in their concrete method IRMv1) and the full non-linear IRM formulation. Additionally, even when capturing the "right" invariances, we show that it is possible for IRM to learn a sub-optimal predictor, due to the loss function not being invariant across environments. The issues arise even when measuring invariance on the population distributions, but are exacerbated by the fact that IRM is extremely fragile to sampling.

📄 PDF Abstract BibTeX arXiv:2101.01134

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Invariance Penalties for Risk Minimization

2021-06-17 · Kia Khezeli, Arno Blaas, Frank Soboczenski, Nicholas Chia 외

The Invariant Risk Minimization (IRM) principle was first proposed by Arjovsky et al. [2019] to address the domain generalization problem by leveraging data heterogeneity from differing experimental conditions. Specifica…

Domain Generalization

Invariant Risk Minimization

2019-07-05 · Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, David Lopez-Paz

We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal …

Domain GeneralizationImage ClassificationOut-of-Distribution Generalization

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

2021-06-11 · NeurIPS 2021 12 · Kartik Ahuja, Ethan Caballero, Dinghuai Zhang, Jean-Christophe Gagnon-Audet 외

The invariance principle from causality is at the heart of notable approaches such as invariant risk minimization (IRM) that seek to address out-of-distribution (OOD) generalization failures. Despite the promising theory…

Out-of-Distribution Generalizationregression

Continual Invariant Risk Minimization

2023-10-21 · Francesco Alesiani, Shujian Yu, Mathias Niepert

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 …

Continual Learning

Robust Reconfigurable Intelligent Surfaces via Invariant Risk and Causal Representations

2021-05-04 · Sumudu Samarakoon, Jihong Park, Mehdi Bennis

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 …