Analyzing Data Selection Techniques with Tools from the Theory of Information Losses
In this paper, we present and illustrate some new tools for rigorously analyzing training data selection methods. These tools focus on the information theoretic losses that occur when sampling data. We use this framework to prove that two methods, Facility Location Selection and Transductive Experimental Design, reduce these losses. These are meant to act as generalizable theoretical examples of applying the field of Information Theoretic Deep Learning Theory to the fields of data selection and active learning. Both analyses yield insight into their respective methods and increase their interpretability. In the case of Transductive Experimental Design, the provided analysis greatly increases the method's scope as well.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningExperimental DesignGeneral ClassificationLearning TheorySimilar Papers 제목 키워드 기반
A Tutorial on Graph Theory for Brain Signal Analysis
This tutorial paper refers to the use of graph-theoretic concepts for analyzing brain signals. For didactic purposes it splits into two parts: theory and application. In the first part, we commence by introducing some ba…
ERPVerdict Accuracy of Quick Reduct Algorithm using Clustering and Classification Techniques for Gene Expression Data
In most gene expression data, the number of training samples is very small compared to the large number of genes involved in the experiments. However, among the large amount of genes, only a small fraction is effective f…
ClusteringDiagnosticfeature selectionGeneral ClassificationStratifying Reinforcement Learning with Signal Temporal Logic
In this paper, we develop a stratification-based semantics for Signal Temporal Logic (STL) in which each atomic predicate is interpreted as a membership test in a stratified space. This perspective reveals a novel corres…
Reinforcement LearningArtisanGS: Interactive Tools for Gaussian Splat Selection with AI and Human in the Loop
Representation in the family of 3D Gaussian Splats (3DGS) are growing into a viable alternative to traditional graphics for an expanding number of application, including recent techniques that facilitate physics simulati…
A Protocol for KG Construction Tasks Involving Users
Knowledge graph construction (KGC) from (semi-)structured data is challenging, and facilitating user involvement is an issue frequently brought up within this community. We cannot deny the progress we have made with resp…
graph construction