Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities | PDF
arxiv.org · 6,723 words · saved by 1 readers
N/A
Published in Transactions on Machine Learning Research (11/2022) Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities Andreas Kirsch andreas.kirsch@cs.ox.ac.uk Yarin Gal yarin.gal@cs.ox.ac.uk…
related reading
- Pen and Paper Exercises in Machine Learningarxiv.org
- [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
- An Introduction to Fisher Information – Awni Hannun – Writing About Machine Learningawni.github.io
- arxiv.org/pdf/1805.08522arxiv.org
- arxiv.org/pdf/2511.08544arxiv.org
- c21f4ce780c5c9d774f79841b81fdc6d-Paper.pdfproceedings.neurips.cc
- catoni_draft2.pdfocatoni.perso.math.cnrs.fr
- Learning with not Enough Data Part 2: Active Learninglilianweng.github.io
- https://arxiv.org/pdf/2006.11239arxiv.org
- RescaledKL.tmdanilorezende.com
- [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
- A Gallery of Methods Beyond RL — Part I: Sampling Methodsshengyu-feng.github.io