Kohei Miyaguchi

Overview

Pronouns

He/Him/His

Location

IBM Research - Tokyo Tokyo, Japan

Bio

Kohei Miyaguchi is a researcher at IBM Research - Tokyo. He is mainly working on machine learning. For more details including his publications, please refer to the external website.

Research Interests

Learning theory and theory-inspired algorithms
Reinforcement learning; offline policy evaluation

Publications

Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies
- - Hiroshi Kajino
  - Kohei Miyaguchi
  - et al.
- 2023
- ICML 2023
Detection of Unobserved Common Cause in Discrete Data Based on the MDL Principle
- - Masatoshi Kobayashi
  - Kohei Miyaguchi
  - et al.
- 2022
- Big Data 2022
Hierarchical Lattice Layer for Partially Monotone Neural Networks
- - Hiroki Yanagisawa
  - Kohei Miyaguchi
  - et al.
- 2022
- NeurIPS 2022
Cumulative Stay-time Representation for Electronic Health Records in Medical Event Time Prediction
- - Takayuki Katsuki
  - Kohei Miyaguchi
  - et al.
- 2022
- IJCAI 2022
Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion
- - Kohei Miyaguchi
  - Takayuki Katsuki
  - et al.
- 2022
- ICLR 2022
Almost Hyperparameter-Free Hyperparameter Selection Framework for Offline Policy Evaluation
- - Kohei Miyaguchi
- 2022
- AAAI 2022
Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models
- - Kohei Miyaguchi
- 2021
- NeurIPS 2021
Adaptive minimax regret against smooth logarithmic losses over high-dimensional L1-balls via envelope complexity
- - Kohei Miyaguchi
  - Kenji Yamanishi
- 2019
- AISTATS 2019
Cogra: Concept-drift-aware stochastic gradient descent for time-series forecasting
- - Kohei Miyaguchi
  - Hiroshi Kajino
- 2019
- AAAI 2019

Top collaborators

Takayuki Katsuki

Researcher

Toshiya Iwamori

Research Scientist

Takayuki Osogami

Senior Technical Staff Member

Akira Koseki

Senior Research Scientist