
Robust Reconfigurable Intelligent Surfaces via Invariant Risk and Causal Representations
In this paper, the problem of robust reconfigurable intelligent surface ...
read it

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

Learning The MMSE Channel Predictor
We present a neural network based predictor which is derived by starting...
read it

LearningAugmented kmeans Clustering
kmeans clustering is a wellstudied problem due to its wide applicabili...
read it

On a simplified version of Hadamard's maximal determinant problem
Hadamard's maximal determinant problem consists in finding the maximal v...
read it

On a Generalization of the Marriage Problem
We present a generalization of the marriage problem underlying Hall's fa...
read it

Unsupervised Bump Hunting Using Principal Components
Principal Components Analysis is a widely used technique for dimension r...
read it
OutofDistribution Generalization with Maximal Invariant Predictor
OutofDistribution (OOD) generalization problem is a problem of seeking the predictor function whose performance in the worst environments is optimal. This paper makes two contributions to OOD problem. We first use the basic results of probability to prove maximal Invariant Predictor(MIP) condition, a theoretical result that can be used to identify the OOD optimal solution. We then use our MIP to derive innerenvironmental Gradient Alignment(IGA) algorithm that can be used to help seek the OOD optimal predictor. Previous studies that have investigated the theoretical aspect of the OODproblem use strong structural assumptions such as causal DAG. However, in cases involving image datasets, for example, the identification of hidden structural relations is itself a difficult problem. Our theoretical results are different from those of many previous studies in that it can be applied to cases in which the underlying structure of a dataset is difficult to analyze. We present an extensive comparison of previous theoretical approaches to the OODproblems based on the assumptions they make. We also present an extension of the coloredMNIST that can more accurately represent the pathological OOD situation than the original version, and demonstrate the superiority of IGA over previous methods on both the original and the extended version of ColoredMNIST.
READ FULL TEXT
Comments
There are no comments yet.