
Invariant Risk Minimization
We introduce Invariant Risk Minimization (IRM), a learning paradigm to e...
read it

Causally Invariant Predictor with ShiftRobustness
This paper proposes an invariant causal predictor that is robust to dist...
read it

OutofDistribution Generalization with Maximal Invariant Predictor
OutofDistribution (OOD) generalization problem is a problem of seeking...
read it

Gated Information Bottleneck for Generalization in Sequential Environments
Deep neural networks suffer from poor generalization to unseen environme...
read it

Nonlinear Invariant Risk Minimization: A Causal Approach
Due to spurious correlations, machine learning systems often fail to gen...
read it

Causallymotivated Shortcut Removal Using Auxiliary Labels
Robustness to certain distribution shifts is a key requirement in many M...
read it

Risk Variance Penalization: From Distributional Robustness to Causality
Learning under multienvironments often requires the ability of outofd...
read it
Robust Reconfigurable Intelligent Surfaces via Invariant Risk and Causal Representations
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 networkbased solution is adopted to seek the predictor and its performance is validated via simulations against an empirical risk minimizationbased design. Results show that leveraging invariance yields more robustness against unseen and outofdistribution testing environments.
READ FULL TEXT
Comments
There are no comments yet.