arXiv AI
A Generalization of Amari's Bayesian Duality
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 2
Everywhere Learning: Artificial Intelligence with Pointwise Constraints
arXiv:2606. 01557v1 Announce Type: new Abstract: Everywhere learning is a new paradigm whereby Artificial Intelligence (AI) systems are trained to satisfy loss constraints with probability one over the data distribution.
arXiv Machine Learning
Jul 22
Information Theoretic Bayesian Optimization over the Probability Simplex
arXiv:2603. 09793v2 Announce Type: replace Abstract: Bayesian optimization is a data-efficient technique that has been shown to be extremely powerful to optimize expensive, black-box, and possibly noisy objective functions.
arXiv Machine Learning
4d ago
Learning Samples Importance: Parameterizing Dual Variables in Everywhere Learning
arXiv:2609.36310v1 Announce Type: new Abstract: Everywhere learning provides a principled framework for training AI models under constraints that must hold throughout the data distribution. In the du...
arXiv Machine Learning
Jul 13
Information-Theoretic Bayesian Optimization for Bilevel Optimization Problems
arXiv:2509. 21725v3 Announce Type: replace Abstract: A bilevel optimization problem consists of two optimization problems nested as an upper- and a lower-level problem, in which the optimality of the lower-level problem defines a constraint for the upper-level problem.
arXiv Machine Learning
Sep 18
Bayesian Optimization with Rich Auxiliary Information via LLMs
The paper introduces Bayesian Optimization (BO) techniques that incorporate rich auxiliary information—such as training curves, expert notes, images, and prior knowledge—using large language models (LLMs). Three new methods are proposed to integrate this auxiliary data into BO, and they are evaluated on hyperparameter optimization benchmarks and a real-world nuclear fusion task. The results show that these LLM-enhanced BO methods consistently outperform standard BO and existing LLM-based optimization approaches.
arXiv Machine Learning
Jun 15
A General Framework for Decision Trees via Bregman Divergences
arXiv:2606. 13984v1 Announce Type: cross Abstract: Decision trees are one of the fundamental tools in statistical learning due to their interpretability, flexibility, and their ability to adapt to nonlinear structures.