2 papers
cs.LG2026
The Bayesian Learning Rule Beyond KL Geometry
Sophia Sklaviadis, Wu Lin, Andre Martins +3
The Bayesian learning rule (BLR) exploits the relation between Bayesian updating and the Kullback-Leibler divergence (KLD) to derive efficient additive updates for exponential fami…
cs.LG2025
The Fenchel-Young Generalization of Bayesian Principles
Sophia Sklaviadis, Thomas Moellenhoff, Andre Martins +2
Conjugate Bayes plays a key role in machine learning, ensuring computationally simple posterior updates. We generalize the variational principle behind this computation by using th…