Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Binary Classification from Coupled Pairwise Labels
Tomoya Tate, Kosuke Sugiyama, Masato Uchida
Even when it is difficult to assign absolute class labels to individual instances, relational information may still be available, such as whether two instances belong to the same c…
cs.LG2026
Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysis
Kosuke Sugiyama, Masato Uchida
This paper proposes an information-theoretic framework for analyzing the theoretical limits of pool-based active learning (AL), in which a subset of instances is selectively labele…
cs.LG2026
Supervised Learning as Lossy Compression: Characterizing Generalization and Sample Complexity via Finite Blocklength Analysis
Kosuke Sugiyama, Masato Uchida
This paper presents a novel information-theoretic perspective on generalization in machine learning by framing the learning problem within the context of lossy compression and appl…