1.4k citations
- The University of TokyoJP116 papers
- RIKENJP81 papers
- Kyoto UniversityJP52 papers
- Keio UniversityJP38 papers
- The University of OsakaJP32 papers
- Tokyo Institute of TechnologyJP27 papers
- Japan Science and Technology AgencyJP25 papers
- National Institute for Materials ScienceJP25 papers
- University of TsukubaJP25 papers
- Japan Atomic Energy AgencyJP21 papers
- Kyushu UniversityJP18 papers
- Nagoya UniversityJP17 papers
54 papers · 1 filter
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\mathc…
Graphical model for factorization and completion of relatively high rank tensors by sparse sampling
Angelo Giorgio Cavaliere, Riki Nagasawa, Shuta Yokoi +2
We consider tensor factorizations based on sparse measurements of the components of relatively high rank tensors. The measurements are designed in a way that the underlying graph o…
Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
Jongyeong Lee, Junya Honda, Shinji Ito +1
This paper studies the optimality of the Follow-the-Perturbed-Leader (FTPL) policy in both adversarial and stochastic -armed bandits. Despite the widespread use of the Follow-th…
How do Transformers perform In-Context Autoregressive Learning?
Michael E. Sander, Raja Giryes, Taiji Suzuki +2
Transformers have achieved state-of-the-art performance in language modeling tasks. However, the reasons behind their tremendous success are still unclear. In this paper, towards a…
Thompson Exploration with Best Challenger Rule in Best Arm Identification
Jongyeong Lee, Junya Honda, Masashi Sugiyama
This paper studies the fixed-confidence best arm identification (BAI) problem in the bandit framework in the canonical single-parameter exponential models. For this problem, many p…
Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes
Charles Riou, Pierre Alquier, Badr-Eddine Chérief-Abdellatif
Bernstein's condition is a key assumption that guarantees fast rates in machine learning. For example, the Gibbs algorithm with prior has an excess risk in , as oppos…