Search Results for author: Kota Matsui

Found 5 papers, 0 papers with code

Automatic Domain Adaptation by Transformers in In-Context Learning

no code implementations27 May 2024 Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi

Selecting or designing an appropriate domain adaptation algorithm for a given problem remains challenging.

Bayesian Active Learning for Structured Output Design

no code implementations9 Nov 2019 Kota Matsui, Shunya Kusakawa, Keisuke Ando, Kentaro Kutsukake, Toru Ujihara, Ichiro Takeuchi

In this paper, we propose an active learning method for an inverse problem that aims to find an input that achieves a desired structured-output.

Active Learning

Parallel Distributed Block Coordinate Descent Methods based on Pairwise Comparison Oracle

no code implementations13 Sep 2014 Kota Matsui, Wataru Kumagai, Takafumi Kanamori

Our algorithm consists of two steps; one is the direction estimate step and the other is the search step.

Cannot find the paper you are looking for? You can Submit a new open access paper.