paper-with-me

Papers

A Practical & Unified Notation for Information-Theoretic Quantities in ML

2021-06-22 · Andreas Kirsch, Yarin Gal

A practical notation can convey valuable intuitions and concisely express new ideas. Information theory is of importance to machine learning, but the notation for information-theoretic quantities is sometimes opaque. We propose a practical and unified notation and extend it to include information-theoretic quantities between observed outcomes (events) and random variables. This includes the point-wise mutual information known in NLP and mixed quantities such as specific surprise and specific information in the cognitive sciences and information gain in Bayesian optimal experimental design. We apply our notation to prove a version of Stirling's approximation for binomial coefficients mentioned by MacKa (2003) using new intuitions. We also concisely rederive the evidence lower bound for variational auto-encoders and variational inference in approximate Bayesian neural networks. Furthermore, we apply the notation to a popular information-theoretic acquisition function in Bayesian active learning which selects the most informative (unlabelled) samples to be labelled by an expert and extend this acquisition function to the core-set problem with the goal of selecting the most informative samples given the labels.

📄 PDF Abstract BibTeX arXiv:2106.12062

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningExperimental DesignVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions

2024-01-09 · Andreas Kirsch

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specificall…

Active LearningDeep Learning

Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework

2026-01-15 · Qingyue Zhang, Chang Chu, Haohao Fu, Tianren Peng 외 arxiv

In multi-source transfer learning, a key challenge lies in how to appropriately differentiate and utilize heterogeneous source tasks. However, existing multi-source methods typically focus on optimizing either the source…

Multi-Task LearningTransfer Learning

Orthogonal Representation Learning for Estimating Causal Quantities

2025-02-06 · Valentyn Melnychuk, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel

Representation learning is widely used for estimating causal quantities (e.g., the conditional average treatment effect) from observational data. While existing representation learning methods have the benefit of allowin…

Representation Learning

Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities

2022-08-01 · Andreas Kirsch, Yarin Gal

Recently proposed methods in data subset selection, that is active learning and active sampling, use Fisher information, Hessians, similarity matrices based on gradients, and gradient lengths to estimate how informative …

Active LearningInformativeness

One if by Land, Two if by Sea, Three if by Four Seas, and More to Come -- Values of Perception, Prediction, Communication, and Common Sense in Decision Making

2025-12-29 · Aolin Xu arxiv

This work aims to rigorously define the values of perception, prediction, communication, and common sense in decision making. The defined quantities are decision-theoretic, but have information-theoretic analogues, e.g.,…

Decision Making