activity
20242026
collaborators

7 papers

stat.ML2026

Information-Theoretic Generalization Bounds for Sequential Decision Making

Futoshi Futami, Masahiro Fujisawa

Information-theoretic generalization bounds based on the supersample construction are a central tool for algorithm-dependent generalization analysis in the batch i.i.d.~setting. Ho…

stat.ML2025

Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables

Futoshi Futami, Masahiro Fujisawa

Latent variables (LVs) play a crucial role in encoder-decoder models by enabling effective data compression, prediction, and generation. Although their theoretical properties, such…

cs.LG2025

Scalable Valuation of Human Feedback through Provably Robust Model Alignment

Masahiro Fujisawa, Masaki Adachi, Michael A. Osborne

Despite the importance of aligning language models with human preferences, crowd-sourced human feedback is often noisy -- for example, preferring less desirable responses -- posing…

cs.LG2025

-Regularized Empirical Risk Minimization Guarantees Small Smooth Calibration Error

Masahiro Fujisawa, Futoshi Futami

Calibration of predicted probabilities is critical for reliable machine learning, yet it is poorly understood how standard training procedures yield well-calibrated models. This wo…

cs.LG2025

PAC-Bayes Analysis for Recalibration in Classification

Masahiro Fujisawa, Futoshi Futami

Nonparametric estimation using uniform-width binning is a standard approach for evaluating the calibration performance of machine learning models. However, existing theoretical ana…

cs.LG2025

Information-theoretic Generalization Analysis for Expected Calibration Error

Futoshi Futami, Masahiro Fujisawa

While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding o…