paper-with-me

Papers

Big Batch Bayesian Active Learning by Considering Predictive Probabilities

2025-01-14 · Sebastian W. Ober, Samuel Power, Tom Diethe, Henry B. Moss

We observe that BatchBALD, a popular acquisition function for batch Bayesian active learning for classification, can conflate epistemic and aleatoric uncertainty, leading to suboptimal performance. Motivated by this observation, we propose to focus on the predictive probabilities, which only exhibit epistemic uncertainty. The result is an acquisition function that not only performs better, but is also faster to evaluate, allowing for larger batches than before.

📄 PDF Abstract BibTeX arXiv:2501.08223

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Batch Bayesian Active Learning with Partial Batch Label Sampling

2025-10-10 · Kangping Hu, Stephen Mussmann arxiv

Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice of which to use. Bayesian-based active learning offers principled objectives wi…

Active Learning

Bayesian Predictive Coding

2025-03-31 · Alexander Tschantz, Magnus Koudahl, Hampus Linander, Lancelot Da Costa 외

Predictive coding (PC) is an influential theory of information processing in the brain, providing a biologically plausible alternative to backpropagation. It is motivated in terms of Bayesian inference, as hidden states …

Bayesian InferenceUncertainty Quantification

Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics

2024-10-14 · Daniel Paulin, Peter A. Whalley, Neil K. Chada, Benedict Leimkuhler

We propose a scalable kinetic Langevin dynamics algorithm for sampling parameter spaces of big data and AI applications. Our scheme combines a symmetric forward/backward sweep over minibatches with a symmetric discretiza…

Practical Deep Learning with Bayesian Principles

2019-06-06 · NeurIPS 2019 12 · Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen 외

Bayesian methods promise to fix many shortcomings of deep learning, but they are impractical and rarely match the performance of standard methods, let alone improve them. In this paper, we demonstrate practical training …

Continual LearningData AugmentationDeep LearningVariational Inference

Informed Initialization for Bayesian Optimization and Active Learning

2025-10-27 · Carl Hvarfner, David Eriksson, Eytan Bakshy, Max Balandat arxiv

Bayesian Optimization is a widely used method for optimizing expensive black-box functions, relying on probabilistic surrogate models such as Gaussian Processes. The quality of the surrogate model is crucial for good opt…

Gaussian ProcessesActive Learning