activity
20182022
most citedA Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning

49 citations · 118 across the 8 of their papers we have counts for

collaborators

14 papers

stat.ML2022

Invariance-adapted decomposition and Lasso-type contrastive learning

Masanori Koyama, Takeru Miyato, Kenji Fukumizu

Recent years have witnessed the effectiveness of contrastive learning in obtaining the representation of dataset that is useful in interpretation and downstream tasks. However, the…

cs.LG20222 cited

Unsupervised Learning of Equivariant Structure from Sequences

Takeru Miyato, Masanori Koyama, Kenji Fukumizu

In this study, we present meta-sequential prediction (MSP), an unsupervised framework to learn the symmetry from the time sequence of length at least three. Our method leverages th…

cs.LG20201 cited

Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective

Ruixiang Zhang, Masanori Koyama, Katsuhiko Ishiguro

Learning controllable and generalizable representation of multivariate data with desired structural properties remains a fundamental problem in machine learning. In this paper, we…

stat.ML2020

Meta Learning as Bayes Risk Minimization

Shin-ichi Maeda, Toshiki Nakanishi, Masanori Koyama

Meta-Learning is a family of methods that use a set of interrelated tasks to learn a model that can quickly learn a new query task from a possibly small contextual dataset. In this…

cs.LG2019

Reconnaissance and Planning algorithm for constrained MDP

Shin-ichi Maeda, Hayato Watahiki, Shintarou Okada +1

Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while…

cs.LG2019

Optuna: A Next-generation Hyperparameter Optimization Framework

Takuya Akiba, Shotaro Sano, Toshihiko Yanase +2

The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that a…