Search papers, labs, and topics across Lattice.
Department of Computer Science, Aalto University, Finland
2
0
5
Neural posteriors are often overconfident with limited data, but DRO-NPE offers a surprisingly simple fix: train against a worst-case loss within a Wasserstein ball.
Real-world experimental design gets a boost: this method adapts to budget limits and changing costs, outperforming existing approaches.
