Seven papers have been accepted at AISTATS 2023, a major conference on machine learning. (As of January 27, 2023)
[Accepted Papers]
- A stopping criterion for Bayesian optimization by the gap of expected minimum simple regrets
Hideaki Ishibashi (Kyushu Institute of Technology)
Masayuki Karasuyama (Nagoya Institute of Technology/RIKEN AIP)
Ichiro Takeuchi (Nagoya University/RIKEN AIP)
Hideitsu Hino (ISM/RIKEN AIP)
- Connectivity-contrastive learning: Combining causal discovery and representation learning for multimodal data
Hiroshi Morioka (RIKEN-AIP)
Aapo Hyvärinen (University of Helsinki)
- Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits
Taira Tsuchiya (Kyoto University / RIKEN)
Shinji Ito (NEC)
Junya Honda (Kyoto University / RIKEN)
- Nyström Method for Accurate and Scalable Implicit Differentiation
Ryuichiro Hataya (RIKEN ADSP/RIKEN AIP)
Makoto Yamada (OIST/Kyoto University/RIKEN AIP)
- The Lie-Group Bayesian Learning Rule
Mehmet Eren Kiral(RIKEN AIP）
Thomas Möllenhoff (RIKEN AIP）
Mohammad Emtiyaz Khan (RIKEN AIP）
- Learning in RKHM: a C*-algebraic twist for kernel machines
Yuka Hashimoto (NTT / RIKEN-AIP)
Masahiro Ikeda (RIKEN-AIP / Keio University)
Hachem Kadri (Aix-Marseille University)
- Scalable Unbalanced Sobolev Transport for Measures on a Graph
Tam Le* (ISM / RIKEN AIP)
Truyen Nguyen* (Onto Innovation)
Kenji Fukumizu (ISM)
(*: equal contribution)
