Search Results for author:
Found 2 papers, 1 papers with code
Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms
First, in the binary classification setup of Rosenfeld et al. (2021), we show that our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments.
Greedy Modality Selection via Approximate Submodular Maximization
We formulate a theoretical framework for optimizing modality selection in multimodal learning and introduce a utility measure to quantify the benefit of selecting a modality.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
