17 papers were accepted at AISTATS 2021, a major conference on machine learning.
[Accepted Papers]
1) Robust Imitation Learning from Noisy Demonstrations
Voot Tangkaratt (RIKEN)
Nontawat Charoenphakdee (The University of Tokyo / RIKEN)
Masashi Sugiyama (RIKEN / The University of Tokyo)
2) Fenchel-Young Losses with Skewed Entropies for Class-posterior Probability Estimation
Han Bao (The University of Tokyo / RIKEN)
Masashi Sugiyama (RIKEN / The University of Tokyo)
3) γ-ABC: Outlier-Robust Approximate Bayesian Computation based on A Robust Divergence Estimator
Masahiro Fujisawa (The University of Tokyo / RIKEN)
Takeshi Teshima (The University of Tokyo / RIKEN)
Issei Sato (The university of Tokyo/RIKEN)
Masashi Sugiyama (RIKEN / The University of Tokyo)
4) A unified view of likelihood ratio and reparameterization gradients
Paavo Parmas (Okinawa Inst. of Sci. and Tech) +
Masashi Sugiyama (RIKEN / The University of Tokyo)
5) On the Memory Mechanism of Tensor-Power Recurrent Models
Hejia Qiu (University of Nottingham)
Chao Li (RIKEN AIP, co-first author)
Ying Weng (University of Nottingham)
Zhun Sun (Bigo Ltd.)
Xingyu He (University of Nottingham)
Qibin Zhao (RIKEN AIP)
6) Flow-based Alignment Approaches for Probability Measures in Different Spaces
Tam Le (RIKEN AIP) *
Naht Ho (The University of Texas Austin) *
Makoto Yamada (Kyoto University / RIKEN AIP)
(*: equal contribution)
7) Entropy Partial Transport with Tree Metrics: Theory and Practice
Tam Le (RIKEN AIP) *
Truyen Nguyen (The University of Akron) *
(*: equal contribution)
8) Regret Minimization for Causal Inference on Large Treatment Space
Akira Tanimoto (NEC)
Tomoya Sakai (NEC)
Takashi Takenouchi (Future University Hakodate / RIKEN AIP)
Hisashi Kashima (Kyoto University / RIKEN AIP)
9) Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint
Yoichi Chikahara (NTT)
Shinsaku Sakaue (NTT)
Akinori Fujino (NTT)
Hisashi Kashima (Kyoto University / RIKEN AIP)
10) Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features
Shingo Yashima (The University of Tokyo)
Atsushi Nitanda (The University of Tokyo / RIKEN AIP / JST-PRESTO)
Taiji Suzuki (The University of Tokyo / RIKEN AIP)
11) Gradient Descent in RKHS with Importance Labeling
Tomoya Murata (NTT DATA Mathematical Systems Inc. / The University of Tokyo)
Taiji Suzuki (The University of Tokyo / RIKEN AIP)
12) A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix
Thang Doan (McGill University / MILA)
Mehdi Bennani (Aqemia)
Bogdan Mazoure (McGill University / MILA)
Guillaume Rabusseau (Université de Montréal / MILA)
Pierre Alquier (RIKEN AIP)
13) On the Number of Linear Functions Composing Deep Neural Network: Towards a Refined Definition of Neural Networks Complexity
Yuuki Takai (RIKEN AIP)
Akiyoshi Sannai (RIKEN AIP)
Matthieu Cordonnier (École Normale Supérieure Paris-Saclay) +
14) Ridge Regression with Overparametrized Networks Converge to Ridgelet Spectrum
Sho Sonoda (RIKEN AIP)
Isao Ishikawa (Ehime University / RIKEN AIP)
Masahiro Ikeda (RIKEN AIP)
15) Mean-Variance Analysis in Bayesian Optimization under Uncertainty.
Shogo Iwazaki (Nagoya Institute of Technology)
Yu Inatsu (Nagoya Institute of Technology)
Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN AIP).
16) Parametric Programming Approach for More Powerful and General Lasso Selective Inference.
Vo Nguyen Le Duy (Nagoya Institute of Technology / RIKEN AIP)
IchiroTakeuchi (Nagoya Institute of Technology / RIKEN AIP)
17) Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain
Takahiro Mimori (RIKEN AIP)
Keiko Sasada (Kumamoto University Hospital, Kumamoto University)
Hirotaka Matsui (Kumamoto University)
Issei Sato (The University of Tokyo / RIKEN AIP / ThinkCyte Inc)
+ Past interns of RIKEN AIP
