| 2025 | ACL | Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding. | Daichi Hayakawa, Issei Sato |
| 2025 | ICLR | Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment. | Naoya Hasegawa, Issei Sato |
| 2025 | ICLR | On the Optimal Memorization Capacity of Transformers. | Tokio Kajitsuka, Issei Sato |
| 2025 | ICML | Benign Overfitting in Token Selection of Attention Mechanism. | Keitaro Sakamoto, Issei Sato |
| 2025 | ICML | On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding. | Kevin Xu, Issei Sato |
| 2024 | ICLR | Exploring Weight Balancing on Long-Tailed Recognition Problem. | Naoya Hasegawa, Issei Sato |
| 2024 | ICLR | Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators? | Tokio Kajitsuka, Issei Sato |
| 2024 | KDD | Top-Down Bayesian Posterior Sampling for Sum-Product Networks. | Soma Yokoi, Issei Sato |
| 2023 | ICLR | Neural Lagrangian Schrdinger Bridge: Diffusion Modeling for Population Dynamics. | Takeshi Koshizuka, Issei Sato |
| 2022 | AISTATS | Pairwise Supervision Can Provably Elicit a Decision Boundary. | Han Bao, Takuya Shimada, Liyuan Xu, Issei Sato, Masashi Sugiyama |
| 2022 | AISTATS | Predictive variational Bayesian inference as risk-seeking optimization. | Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, Masashi Sugiyama |
| 2022 | ICLR | Disentanglement Analysis with Partial Information Decomposition. | Seiya Tokui, Issei Sato |
| 2022 | ICML | Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum. | Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama |
| 2022 | IJCAI | Evaluation Methods for Representation Learning: A Survey. | Kento Nozawa, Issei Sato |
| 2021 | AISTATS | γ-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator. | Masahiro Fujisawa, Takeshi Teshima, Issei Sato, Masashi Sugiyama |
| 2021 | AISTATS | Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain. | Takahiro Mimori, Keiko Sasada, Hirotaka Matsui, Issei Sato |
| 2021 | ICLR | A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima. | Zeke Xie, Issei Sato, Masashi Sugiyama |
| 2021 | ICML | Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification. | Nan Lu, Shida Lei, Gang Niu, Issei Sato, Masashi Sugiyama |
| 2021 | SIGGRAPH | User interfaces for high-dimensional design problems: from theories to implementations. | Yonghao Yue, Yuki Koyama, Issei Sato, Takeo Igarashi |
| 2021 | SAS | Toward Neural-Network-Guided Program Synthesis and Verification. | Naoki Kobayashi, Taro Sekiyama, Issei Sato, Hiroshi Unno |
| 2020 | ICIP | A Comparison Of Compressed Sensing And Dnn Based Reconstruction For Ghost Motion Imaging. | Mantaro Yamada, Hiroaki Adachi, Ryoichi Horisaki, Issei Sato |
| 2020 | ICML | Accelerating the diffusion-based ensemble sampling by non-reversible dynamics. | Futoshi Futami, Issei Sato, Masashi Sugiyama |
| 2020 | ICML | Few-shot Domain Adaptation by Causal Mechanism Transfer. | Takeshi Teshima, Issei Sato, Masashi Sugiyama |
| 2020 | ICML | Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis. | Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama |
| 2019 | AAAI | Bayesian Posterior Approximation via Greedy Particle Optimization. | Futoshi Futami, Zhenghang Cui, Issei Sato, Masashi Sugiyama |
| 2019 | AAAI | Unsupervised Domain Adaptation Based on Source-Guided Discrepancy. | Seiichi Kuroki, Nontawat Charoenphakdee, Han Bao, Junya Honda, Issei Sato, Masashi Sugiyama |
| 2019 | AAAI | Clipped Matrix Completion: A Remedy for Ceiling Effects. | Takeshi Teshima, Miao Xu, Issei Sato, Masashi Sugiyama |
| 2019 | CVPR | On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions. | Yusuke Tsuzuku, Issei Sato |
| 2019 | CVPR | Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping. | Xi Yang, Bojian Wu, Issei Sato, Takeo Igarashi |
| 2018 | AISTATS | Bayesian Nonparametric Poisson-Process Allocation for Time-Sequence Modeling. | Hongyi Ding, Mohammad Emtiyaz Khan, Issei Sato, Masashi Sugiyama |
| 2018 | AISTATS | Variational Inference based on Robust Divergences. | Futoshi Futami, Issei Sato, Masashi Sugiyama |
| 2018 | ICML | Does Distributionally Robust Supervised Learning Give Robust Classifiers? | Weihua Hu, Gang Niu, Issei Sato, Masashi Sugiyama |
| 2018 | ICML | Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model. | Hideaki Imamura, Issei Sato, Masashi Sugiyama |
| 2018 | KDD | Managing Computer-Assisted Detection System Based on Transfer Learning with Negative Transfer Inhibition. | Issei Sato, Yukihiro Nomura, Shouhei Hanaoka, Soichiro Miki, Naoto Hayashi, Osamu Abe, Yoshitaka Masutani |
| 2018 | UAI | Variational Inference for Gaussian Processes with Panel Count Data. | Hongyi Ding, Young Lee, Issei Sato, Masashi Sugiyama |
| 2017 | ACML | A Quantum-Inspired Ensemble Method and Quantum-Inspired Forest Regressors. | Zeke Xie, Issei Sato |
| 2017 | ICML | Evaluating the Variance of Likelihood-Ratio Gradient Estimators. | Seiya Tokui, Issei Sato |
| 2016 | AAAI | Infinite Plaid Models for Infinite Bi-Clustering. | Katsuhiko Ishiguro, Issei Sato, Masahiro Nakano, Akisato Kimura, Naonori Ueda |
| 2016 | ICDM | Model-Based Approaches for Independence-Enhanced Recommendation. | Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, Issei Sato |
| 2015 | AAAI | The Hybrid Nested/Hierarchical Dirichlet Process and its Application to Topic Modeling with Word Differentiation. | Tengfei Ma, Issei Sato, Hiroshi Nakagawa |
| 2015 | KDD | Stochastic Divergence Minimization for Online Collapsed Variational Bayes Zero Inference of Latent Dirichlet Allocation. | Issei Sato, Hiroshi Nakagawa |
| 2015 | PAKDD | Locally Optimized Hashing for Nearest Neighbor Search. | Seiya Tokui, Issei Sato, Hiroshi Nakagawa |
| 2015 | SIGMOD | Bayesian Differential Privacy on Correlated Data. | Bin Yang, Issei Sato, Hiroshi Nakagawa |
| 2014 | EMNLP | Formalizing Word Sampling for Vocabulary Prediction as Graph-based Active Learning. | Yo Ehara, Yusuke Miyao, Hidekazu Oiwa, Issei Sato, Hiroshi Nakagawa |
| 2014 | ICML | Latent Confusion Analysis by Normalized Gamma Construction. | Issei Sato, Hisashi Kashima, Hiroshi Nakagawa |
| 2014 | ICML | Approximation Analysis of Stochastic Gradient Langevin Dynamics by using Fokker-Planck Equation and Ito Process. | Issei Sato, Hiroshi Nakagawa |
| 2013 | ACML | Multi-armed Bandit Problem with Lock-up Periods. | Junpei Komiyama, Issei Sato, Hiroshi Nakagawa |
| 2012 | ACL | Reducing Wrong Labels in Distant Supervision for Relation Extraction. | Shingo Takamatsu, Issei Sato, Hiroshi Nakagawa |
| 2012 | COLING | Mining Words in the Minds of Second Language Learners: Learner-Specific Word Difficulty. | Yo Ehara, Issei Sato, Hidekazu Oiwa, Hiroshi Nakagawa |
| 2012 | HCOMP | Learning from Crowds and Experts. | Hiroshi Kajino, Yuta Tsuboi, Issei Sato, Hisashi Kashima |
| 2012 | ICML | Rethinking Collapsed Variational Bayes Inference for LDA. | Issei Sato, Hiroshi Nakagawa |
| 2012 | KDD | Practical collapsed variational bayes inference for hierarchical dirichlet process. | Issei Sato, Kenichi Kurihara, Hiroshi Nakagawa |
| 2012 | PAKDD | Privacy-Preserving EM Algorithm for Clustering on Social Network. | Bin Yang, Issei Sato, Hiroshi Nakagawa |
| 2011 | ICDM | Secure Clustering in Private Networks. | Bin Yang, Issei Sato, Hiroshi Nakagawa |
| 2011 | PAKDD | Probabilistic Matrix Factorization Leveraging Contexts for Unsupervised Relation Extraction. | Shingo Takamatsu, Issei Sato, Hiroshi Nakagawa |
| 2010 | KDD | Topic models with power-law using Pitman-Yor process. | Issei Sato, Hiroshi Nakagawa |
| 2010 | KDD | Collusion-resistant privacy-preserving data mining. | Bin Yang, Hiroshi Nakagawa, Issei Sato, Jun Sakuma |
| 2010 | PAKDD | Mining Numbers in Text Using Suffix Arrays and Clustering Based on Dirichlet Process Mixture Models. | Minoru Yoshida, Issei Sato, Hiroshi Nakagawa, Akira Terada |
| 2010 | SIGIR | Person name disambiguation by bootstrapping. | Minoru Yoshida, Masaki Ikeda, Shingo Ono, Issei Sato, Hiroshi Nakagawa |
| 2009 | UAI | Quantum Annealing for Variational Bayes Inference. | Issei Sato, Kenichi Kurihara, Shu Tanaka, Hiroshi Nakagawa, Seiji Miyashita |
| 2008 | KDD | Knowledge discovery of semantic relationships between words using nonparametric bayesian graph model. | Issei Sato, Minoru Yoshida, Hiroshi Nakagawa |
| 2008 | PAKDD | Person Name Disambiguation in Web Pages Using Social Network, Compound Words and Latent Topics. | Shingo Ono, Issei Sato, Minoru Yoshida, Hiroshi Nakagawa |
| 2007 | EMNLP | Bayesian Document Generative Model with Explicit Multiple Topics. | Issei Sato, Hiroshi Nakagawa |
| 2007 | KDD | Knowledge discovery of multiple-topic document using parametric mixture model with dirichlet prior. | Issei Sato, Hiroshi Nakagawa |
| 2007 | PAKDD | Semi-structure Mining Method for Text Mining with a Chunk-Based Dependency Structure. | Issei Sato, Hiroshi Nakagawa |
| 2006 | ICDE | Text Mining using PrefixSpan constrained by Item Interval and Item Attribute. | Issei Sato, Yu Hirate, Hayato Yamana |