An IPM-based framework for Bayesian optimal experimental design is proposed that replaces KL-based expected information gain with Wasserstein, MMD, and energy distances, delivering stronger stability guarantees and plug-and-play extensions.
Claudio Lucchese, Franco Maria Nardini, Salvatore Or- lando, Raffaele Perego, and Alberto Veneri
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DenoiseRank uses diffusion models to learn rankings by noising relevant labels and denoising them to predict label distributions for query-document pairs.
Safety certification of dynamical systems is reformulated as direct classification via kernel embeddings on trajectories, bypassing recursive DP to avoid error compounding and support non-Markovian dynamics.
citing papers explorer
-
Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions
An IPM-based framework for Bayesian optimal experimental design is proposed that replaces KL-based expected information gain with Wasserstein, MMD, and energy distances, delivering stronger stability guarantees and plug-and-play extensions.
-
DenoiseRank: Learning to Rank by Diffusion Models
DenoiseRank uses diffusion models to learn rankings by noising relevant labels and denoising them to predict label distributions for query-document pairs.
-
Safety Certification is Classification
Safety certification of dynamical systems is reformulated as direct classification via kernel embeddings on trajectories, bypassing recursive DP to avoid error compounding and support non-Markovian dynamics.