120 citations · 305 across the 23 of their papers we have counts for
23 papers
Benign Overfitting under Learning Rate Conditions for Sub-exponential Input
Kota Okudo, Kei Kobayashi
This paper investigates the phenomenon of benign overfitting in binary classification problems with heavy-tailed input distributions, extending the analysis of maximum margin class…
Heat content for Gaussian processes: small-time asymptotic analysis
Kei Kobayashi, Hyunchul Park
This paper establishes the small-time asymptotic behaviors of the regular heat content and spectral heat content for general Gaussian processes in both one-dimensional and multi-di…
A unified approach to the small-time behavior of the spectral heat content for isotropic Lévy processes
Kei Kobayashi, Hyunchul Park
This paper establishes the precise small-time asymptotic behavior of the spectral heat content for isotropic Lévy processes on bounded open sets of with…
Large-time and small-time behaviors of the spectral heat content for time-changed stable processes
Kei Kobayashi, Hyunchul Park
We study the large-time and small-time asymptotic behaviors of the spectral heat content for time-changed stable processes, where the time change belongs to a large class of invers…
Representing Hierarchical Structure by Using Cone Embedding
Daisuke Takehara, Kei Kobayashi
Graph embedding is becoming an important method with applications in various areas, including social networks and knowledge graph completion. In particular, Poincaré embedding has…
Entropy-regularized optimal transport on multivariate normal and q-normal distributions
Qijun Tong, Kei Kobayashi
The distance and divergence of the probability measures play a central role in statistics, machine learning, and many other related fields. The Wasserstein distance has received mu…