collaborators

5 papers

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…

cs.LG2026

Learning from Similarity-Confidence and Confidence-Difference

Tomoya Tate, Kosuke Sugiyama, Masato Uchida

In practical machine learning applications, it is often challenging to assign accurate labels to data, and increasing the number of labeled instances is often limited. In such case…

cs.LG2026

Learning from Similarity/Dissimilarity and Pairwise Comparison

Tomoya Tate, Kosuke Sugiyama, Masato Uchida

This paper addresses binary classification in scenarios where obtaining explicit instance level labels is impractical, by exploiting multiple weak labels defined on instance pairs.…

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.LG2025

Learning from Hard Labels with Additional Supervision on Non-Hard-Labeled Classes

Kosuke Sugiyama, Masato Uchida

In scenarios where training data is limited due to observation costs or data scarcity, enriching the label information associated with each instance becomes crucial for building hi…