111 citations · 283 across the 44 of their papers we have counts for
48 papers
Adaptive Normalized Gradient Method for -smooth Problems: Estimating Problem Parameters as a Region
Rikiya Okazaki, Shotaro Yagishita, Hideitsu Hino
We propose a parameter-free and efficient gradient descent algorithm for -smooth optimization. This notion of smoothness, introduced by Zhang et al. (2020), allows the s…
Generalized Determinantal Point Processes for Attraction and Repulsion with Distinct Interaction Kernels
Hideaki Ishibashi, Takahiro Kawashima, Hideitsu Hino
Determinantal point processes (DPPs) model subset selection probability with repulsion, but many applications also exhibit attraction arising from pairwise relations or shared late…
Scalable Learning of Determinantal Point Processes with Kernel-Structured Interactions
Takahiro Kawashima, Hideitsu Hino
Determinantal point processes (DPPs) on a finite set are probability models that exhibit repulsion where inter-item similarities are encoded by a positive definite kernel matrix. S…
Knowledge Distillation under Teacher Misspecification: An Order-Parameter Analysis of the Gap between Teacher Mimicry and Task Performance
Kazuyuki Hara, Hideitsu Hino
Knowledge distillation trains a small student model to reproduce the outputs of a large teacher model, and its progress is typically monitored through the teacher--student discrepa…
Determinantal Point Process Approximation under Positive and Negative Dependence
So Anzai, Hideitsu Hino
Determinantal point processes (DPPs) are widely used as probabilistic models for diverse random subsets, but their approximation error under model misspecification has not been ful…
Projective Maximum Entropy: Universality and Acceptance-Region Calibration
Hideitsu Hino
Maximum-entropy reference distributions are usually constructed on the normalized probability simplex. This formulation is less natural for unnormalized statistical models, in whic…
LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers
Eight Suzuki, Hideitsu Hino, Noboru Murata
Transformers achieve strong performance, but their internal computations remain opaque. We view each Transformer layer as a dynamic graph whose nodes are token representations and…
From DPPs to -DPPs: identifiability analysis via spectral decomposition
Hideitsu Hino, Keisuke Yano
We study the geometry of determinantal point processes (DPPs) through the spectral decomposition . The spectrum governs the cardinality distribution via elementar…
Sobolev--Ricci Curvature
Kyoichi Iwasaki, Tam Le, Hideitsu Hino
Ricci curvature is a fundamental concept in differential geometry for encoding local geometric structure, and its graph-based analogues have recently gained prominence as practical…
Generalized Sobolev IPM for Graph-Based Measures
Tam Le, Truyen Nguyen, Hideitsu Hino +1
We study the Sobolev IPM problem for measures supported on a graph metric space, where critic function is constrained to lie within the unit ball defined by Sobolev norm. While Le…
Misspecifying non-compensatory as compensatory IRT: analysis of estimated skills and variance
Hiroshi Tamano, Hideitsu Hino, Daichi Mochihashi
Multidimensional item response theory is a statistical test theory used to estimate the latent skills of learners and the difficulty levels of problems based on test results. Both…
Complex non-backtracking matrix for directed graphs
Keishi Sando, Hideitsu Hino
Graph representation matrices are essential tools in graph data analysis. Recently, Hermitian adjacency matrices have been proposed to investigate directed graph structures. Previo…
An -accurate level set estimation with a stopping criterion
Hideaki Ishibashi, Kota Matsui, Kentaro Kutsukake +1
The level set estimation problem seeks to identify regions within a set of candidate points where an unknown and costly to evaluate function's value exceeds a specified threshold,…
An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph
Tam Le, Truyen Nguyen, Hideitsu Hino +1
We investigate optimal transport (OT) for measures on graph metric spaces with different total masses. To mitigate the limitations of traditional geometry, Orlicz-Wasserstein…
Scalable Sobolev IPM for Probability Measures on a Graph
Tam Le, Truyen Nguyen, Hideitsu Hino +1
We investigate the Sobolev IPM problem for probability measures supported on a graph metric space. Sobolev IPM is an important instance of integral probability metrics (IPM), and i…
A Family of Distributions of Random Subsets for Controlling Positive and Negative Dependence
Takahiro Kawashima, Hideitsu Hino
Positive and negative dependence are fundamental concepts that characterize the attractive and repulsive behavior of random subsets. Although some probabilistic models are known to…
Duality induced by an embedding structure of determinantal point process
Hideitsu Hino, Keisuke Yano
This paper investigates the information geometrical structure of a determinantal point process (DPP). It demonstrates that a DPP is embedded in the exponential family of log-linear…
A Short Survey on Importance Weighting for Machine Learning
Masanari Kimura, Hideitsu Hino
Importance weighting is a fundamental procedure in statistics and machine learning that weights the objective function or probability distribution based on the importance of the in…
Scalable Counterfactual Distribution Estimation in Multivariate Causal Models
Thong Pham, Shohei Shimizu, Hideitsu Hino +1
We consider the problem of estimating the counterfactual joint distribution of multiple quantities of interests (e.g., outcomes) in a multivariate causal model extended from the cl…
Information Geometrically Generalized Covariate Shift Adaptation
Masanari Kimura, Hideitsu Hino
Many machine learning methods assume that the training and test data follow the same distribution. However, in the real world, this assumption is very often violated. In particular…
Active Learning by Query by Committee with Robust Divergences
Hideitsu Hino, Shinto Eguchi
Active learning is a widely used methodology for various problems with high measurement costs. In active learning, the next object to be measured is selected by an acquisition func…
Unsupervised Domain Adaptation for Extra Features in the Target Domain Using Optimal Transport
Toshimitsu Aritake, Hideitsu Hino
Domain adaptation aims to transfer knowledge of labeled instances obtained from a source domain to a target domain to fill the gap between the domains. Most domain adaptation metho…
Gaussian Process Koopman Mode Decomposition
Takahiro Kawashima, Hideitsu Hino
In this paper, we propose a nonlinear probabilistic generative model of Koopman mode decomposition based on an unsupervised Gaussian process. Existing data-driven methods for Koopm…
Geometry of EM and related iterative algorithms
Hideitsu Hino, Shotaro Akaho, Noboru Murata
The Expectation--Maximization (EM) algorithm is a simple meta-algorithm that has been used for many years as a methodology for statistical inference when there are missing measurem…