paper-with-me

Papers

Training Neural Networks with Optimal Double-Bayesian Learning

2026-05-19 · Vy Bui, Hang Yu, Karthik Kantipudi, Ziv Yaniv, Stefan Jaeger arxiv

Backpropagation with gradient descent is a common optimization strategy employed by most neural network architectures in machine learning. However, finding optimal hyperparameters to guide training has proven challenging. While it is widely acknowledged that selecting appropriate parameters is crucial for avoiding overfitting and achieving unbiased outcomes, this choice remains largely based on empirical experiments and experience. This paper presents a new probabilistic framework for the learning rate, a key parameter in stochastic gradient descent. The framework develops classic Bayesian statistics into a double-Bayesian decision mechanism involving two antagonistic Bayesian processes. A theoretically optimal learning rate can be derived from these two processes and used for stochastic gradient descent. Experiments across various classification, segmentation, and detection tasks corroborate the practical significance of the theoretically derived learning rate. The paper also discusses the ramifications of the proposed double-Bayesian framework for network training and model performance.

📄 PDF Abstract BibTeX arXiv:2605.20009

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Accelerated Bayesian Optimal Experimental Design via Conditional Density Estimation and Informative Data

2025-07-21 · Miao Huang, Hongqiao Wang, Kunyu Wu arxiv

The Design of Experiments (DOEs) is a fundamental scientific methodology that provides researchers with systematic principles and techniques to enhance the validity, reliability, and efficiency of experimental outcomes. …

Density Estimation

Probabilistic Bayesian optimal experimental design using conditional normalizing flows

2024-02-28 · Rafael Orozco, Felix J. Herrmann, Peng Chen

Bayesian optimal experimental design (OED) seeks to conduct the most informative experiment under budget constraints to update the prior knowledge of a system to its posterior from the experimental data in a Bayesian fra…

Experimental Design

Bayesian bandits: balancing the exploration-exploitation tradeoff via double sampling

2017-09-10 · Iñigo Urteaga, Chris H. Wiggins

Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorith…

Reinforcement LearningThompson Sampling

Double-Bayesian Learning

2024-10-16 · Stefan Jaeger

Contemporary machine learning methods will try to approach the Bayes error, as it is the lowest possible error any model can achieve. This paper postulates that any decision is composed of not one but two Bayesian decisi…

Decision Making

Contrasting random and learned features in deep Bayesian linear regression

2022-03-01 · Jacob A. Zavatone-Veth, William L. Tong, Cengiz Pehlevan

Understanding how feature learning affects generalization is among the foremost goals of modern deep learning theory. Here, we study how the ability to learn representations affects the generalization performance of a si…

Learning Theoryregression