2024.05.31 The following papers have been accepted for publication in TMLR.
Keitaro Sakamoto and Issei Sato.
End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training

2024.05.17 The following papers have been accepted for publication in KDD2024．
Soma Yokoi and Issei Sato
Top-Down Bayesian Posterior Sampling for Sum-Product Networks

2024.01.17 The following papers have been accepted for publication in ICLR2024.
Tokio Kajitsuka and Issei Sato.
Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?.
Naoya Hasegawa and Issei Sato.
Exploring Weight Balancing on Long-Tailed Recognition Problem.

2023.10.06 The following paper has been accepted for publication in Nature comunications.　
Masakazu Agetsuma, Issei Sato, Yasuhiro R. Tanaka, Luis Carrillo-Reid, Atsushi Kasai, Atsushi Noritake, Yoshiyuki Arai, Miki Yoshitomo, Takashi Inagaki, Hiroshi Yukawa, Hitoshi Hashimoto, Junichi Nabekura & Takeharu Nagai. Activity-dependent organization of prefrontal hub-networks for associative learning and signal transformation.

2023.09.25 The following paper has been accepted for publication in Neurips2023．
Zeke Xie, zhiqiang xu, Jingzhao Zhang, Issei Sato, Masashi Sugiyama. On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective.

2023.04.01 Dr. Ryoaki Kawase has joined as an Assistant Professor.

2023.01.21 The following paper has been accepted for publication in ICLR2023 as a lspotlight (notable-top-25%)
Takeshi Koshizuka, Issei Sato. Schrödinger Bridge: Diffusion Modeling for Population Dynamics.

2022.09.15 The following papers have been accepted for publication in NeurIPS2022.
Mingcheng Hou and Issei Sato. A Closer Look at Prototype Classifier for Few-shot Image Classification.
Keitaro Sakamoto and Issei Sato. Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective.

2022.05.15. The following papers have been accepted for publication in ICML2022 as a long presentation.
Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, and Masashi Sugiyama. Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum.

2022.02.17. The following papers have been accepted for publication in Neural computation.

Zhenghang Cui and Issei Sato. Active Classification With Uncertainty Comparison Queries.

2022.01.21. The following paper has been accepted for publication in ICLR2022.

Seiya Tokui and Issei Sato. Disentanglement Analysis with Partial Information Decomposition.

2022.01.18. The following papers have been accepted for publication in AISTATS2022.

Han Bao, Takuya Shimada, Liyuan Xu, Issei Sato, Masashi Sugiyama. Pairwise Supervision Can Provably Elicit a Decision Boundary.
Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, Masashi Sugiyama. Predictive variational Bayesian inference as risk-seeking optimization.

2021.09.29. The following papers have been accepted for publication in NeurIPS2021.

Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, and Masashi Sugiyama. Loss function based second-order Jensen inequality and its application to particle variational inference.

Kento Nozawa and Issei Sato. Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning.

2021.08.12. The following course work has been accepted for publication in SIGGRAPH2021.

Yonghao Yue, Yuki Koyama, Issei Sato, Takeo Igarashi. User interfaces for high-dimensional design problems: from theories to implementations.

2021.08.11. The following paper has been accepted for publication in International Journal of Computer Assisted Radiology and Surgery.

Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura, Takahiro Nakao, Issei Sato, Daisuke Sato, Naoto Hayashi, Osamu Abe. A versatile anomaly detection method for medical images with a flow-based generative model in semi-supervision setting.

2021.07.30. The following paper has been accepted for publication in Entropy.

Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato. Accelerated Diffusion-Based Sampling by the Non-Reversible Dynamics with Skew-Symmetric Matrices.

2021.05.28. The following paper has been accepted for publication in Neural Computation．

Taira Tsuchiya, Nontawat Charoenphakdee, Issei Sato, & Masashi Sugiyama. Semi-supervised ordinal regression based on empirical risk minimization.

2021.05.15. The following paper has been accepted for publication in Neural Computation.

Takuya Shimada, Han Bao, Issei Sato, Masashi Sugiyama. Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization.

2021.05.08. The following paper has been accepted for publication in ICML2021．

Nan Lu, Shida Lei, Gang Niu, Issei Sato, Masashi Sugiyama. Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification.

2021.02.23. The following paper has been accepted for publication in Neural Computation．

Zeke Xie, Fengxiang He, Shaopeng Fu, Issei Sato, Dacheng Tao, Masashi Sugiyama. Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting.

2021. 01. 23. The following papers have been accepted for publication in AISTATS2021．

Takahiro Mimori, Keiko Sasada, Hirotaka Matsui, and Issei Sato. Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain.

Masahiro Fujisawa, Takeshi Teshima, Issei Sato, and Masashi Sugiyama. γ-ABC: Outlier-robust approximate Bayesian computation based on a robust divergence estimator.

2021. 01. 13. The following paper has been accepted for publication in ICLR2021．

Zeke Xie, Issei Sato, Masashi Sugiyama. A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima.

2020. 12. 29 The following paper has been accepted for publication in Computer Graphics Forum．

Toby Chong, I‐Chao Shen, Issei Sato, and Takeo Igarashi. Interactive Optimization of Generative Image Modelling using Sequential Subspace Search and Content‐based Guidance.

2020. 09. 06 The following paper has been accepted for publication in Machine learning journal．

Soma Yokoi, Takuma Otsuka, and Issei Sato. Weak approximation of transformed stochastic gradient MCMC.

2020. 06. 01 The following papers have been accepted for publication in ICML2020．

Futoshi Futami, Issei Sato, and Masashi Sugiyama. Accelerating the diffusion-based ensemble sampling by non-reversible dynamics.

Takeshi Teshima, Issei Sato, and Masashi Sugiyama. Few-shot domain adaptation by causal mechanism transfer.

Yusuke Tsuzuku, Issei Sato, and Masashi Sugiyama. Normalized flat minima: Exploring scale invariant definition of flat minima for neural networks using PAC-Bayesian analysis.

2020. 05. 01 The following paper has been accepted for publication in SIGGRAPH 2020．

Yuki Koyama, Issei Sato, and Masataka Goto. 2020. Sequential Gallery for Interactive Visual Design Optimization.

2020.03.09 The following paper has been accepted for publication in International Journal of Computer Assisted Radiology and Surgery.

Yukihiro Nomura, Soichiro Miki, Naoto Hayashi, Shouhei Hanaoka, Issei Sato, Takeharu Yoshikawa, Yoshitaka Masutani, and Osamu Abe. Novel platform for development, training, and validation of computer-assisted detection/diagnosis software.

2020. 03. 01 The following paper has been accepted for publication in Neural Computation．

Zhenghang Cui , Nontawat Charoenphakdee , Issei Sato, and Masashi Sugiyama. Classification from Triplet Comparison Data.

2020. 01. 20 The following paper has been accepted for publication in The Journal of Supercomputing．

Yukihiro Nomura, Issei Sato, Toshihiro Hanawa, Shouhei Hanaoka, Takahiro Nakao, Tomomi Takenaga, Tetsuya Hoshino, Yuji Sekiya, Soichiro Miki, Takeharu Yoshikawa, Naoto Hayashi , Osamu Abe. Development of training environment for deep learning with medical images on supercomputer system based on asynchronous parallel Bayesian optimization.