1 citations · 1 across the 7 of their papers we have counts for
8 papers
Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statistics
Masanari Kimura
This study develops a higher-order asymptotic framework for test-time adaptation (TTA) of Batch Normalization (BN) statistics under distribution shift by integrating classical Edge…
Graph-Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry
Masanari Kimura
Label shift adaptation aims to recover target class priors when the labelled source distribution and the unlabelled target distribution share bu…
Generalized Power Priors for Improved Bayesian Inference with Historical Data
Masanari Kimura, Howard Bondell
The power prior is a class of informative priors designed to incorporate historical data alongside current data in a Bayesian framework. It includes a power parameter that controls…
Edgeworth Expansion for Semi-hard Triplet Loss
Masanari Kimura
We develop a higher-order asymptotic analysis for the semi-hard triplet loss using the Edgeworth expansion. It is known that this loss function enforces that embeddings of similar…
Heteroscedastic Double Bayesian Elastic Net
Masanari Kimura
In many practical applications, regression models are employed to uncover relationships between predictors and a response variable, yet the common assumption of constant error vari…
Theoretical and Practical Analysis of Fréchet Regression via Comparison Geometry
Masanari Kimura, Howard Bondell
Fréchet regression extends classical regression methods to non-Euclidean metric spaces, enabling the analysis of data relationships on complex structures such as manifolds and grap…
Test-Time Augmentation Meets Variational Bayes
Masanari Kimura, Howard Bondell
Data augmentation is known to contribute significantly to the robustness of machine learning models. In most instances, data augmentation is utilized during the training phase. Tes…
Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds
Masanari Kimura, Howard Bondell
The density ratio of two probability distributions is one of the fundamental tools in mathematical and computational statistics and machine learning, and it has a variety of known…