← Search

Amin Behjati

2 accepted papers

2024

Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization

NeurIPS 2024poster

The aim of this paper is to address the challenge of gradual domain adaptation within a class of manifold-constrained data distributions. In particular, we consider a sequence of $T\ge2$ data distributions $P_1,\ldots,P_T$ undergoing a gradual shift, where each pair of consecutive measures $P_i,P_{i…

Cited by 0SourcePDFScholar
2024

More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms

ICML 2024poster

We introduce a new framework for studying meta-learning methods using PAC-Bayesian theory. Its main advantage over previous work is that it allows for more flexibility in how the transfer of knowledge between tasks is realized. For previous approaches, this could only happen indirectly, by means of…