← Authors

Issei Sato

54 papers · 2007–2025 · 13 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) πŸ—ΊοΈ Taxonomy Completionist (20) 🧭 Keyword Pioneer πŸƒ Academic Marathon (18) 🌍 Conference Polyglot (13) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (21) πŸ‘‘ Triple Crown 🧬 Topic Evolution πŸ† Grand Slam πŸ”¬ Deep Specialist (13) πŸ† Keyword Champion πŸš€ Conference Pioneer ⚑ Prolific Year (7) πŸ”₯ Unstoppable (10) ❓ The Questioner (2) πŸ“ˆ Trend Setter πŸ’Ž Century Club (54) πŸ—ƒοΈ Keyword Collector (197)

Conferences

NIPS (13) ICML (12) ICLR (7) AISTATS (6) AAAI (3) EMNLP (3) ACL (2) ACML (2) JMLR (2) COLING (1) CONLL (1) CVPR (1) IJCAI (1)

Top co-authors

Masashi Sugiyama (21) Hiroshi Nakagawa (11) Futoshi Futami (6) Zeke Xie (4) Masahiro Fujisawa (3) Hidekazu Oiwa (3) Takeshi Teshima (3) Yusuke Tsuzuku (3) Naonori Ueda (3) Yo Ehara (3)

Keywords

bayesian inference (7) variational inference (6) generalization bound (4) representation learning (3) outlier robustness (2) posterior approximation (2) bayesian nonparametric (2) stochastic gradient descent (2) theoretical analysis (2) neural network optimization (2) latent dirichlet allocation (2) variance reduction (2) online learning (2) few-shot learning (2) stochastic optimization (2) topic modeling (2) probabilistic modeling (2) binary classification (2) generalization error (2) adversarial perturbation (2)

Papers

Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment ICLR 2025
Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding ACL 2025
Benign Overfitting in Token Selection of Attention Mechanism ICML 2025
On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding ICML 2025
On the Optimal Memorization Capacity of Transformers ICLR 2025
Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective NIPS 2024
Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective NIPS 2024
Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators? ICLR 2024
Exploring Weight Balancing on Long-Tailed Recognition Problem ICLR 2024
Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics ICLR 2023
On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective NIPS 2023
Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective NIPS 2022
Pairwise Supervision Can Provably Elicit a Decision Boundary AISTATS 2022
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum ICML 2022
Evaluation Methods for Representation Learning: A Survey IJCAI 2022
A Closer Look at Prototype Classifier for Few-shot Image Classification NIPS 2022
Predictive variational Bayesian inference as risk-seeking optimization AISTATS 2022
Disentanglement Analysis with Partial Information Decomposition ICLR 2022
Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning NIPS 2021
Loss function based second-order Jensen inequality and its application to particle variational inference NIPS 2021
Ξ³-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator AISTATS 2021
Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain AISTATS 2021
A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima ICLR 2021
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification ICML 2021
Multilevel Monte Carlo Variational Inference JMLR 2021
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis ICML 2020
Few-shot Domain Adaptation by Causal Mechanism Transfer ICML 2020
Accelerating the diffusion-based ensemble sampling by non-reversible dynamics ICML 2020
Unsupervised Domain Adaptation Based on Source-Guided Discrepancy AAAI 2019
On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions CVPR 2019
Bayesian Posterior Approximation via Greedy Particle Optimization AAAI 2019
Clipped Matrix Completion: A Remedy for Ceiling Effects AAAI 2019
Does Distributionally Robust Supervised Learning Give Robust Classifiers? ICML 2018
Bayesian Nonparametric Poisson-Process Allocation for Time-Sequence Modeling AISTATS 2018
Variational Inference based on Robust Divergences AISTATS 2018
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks NIPS 2018
Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model ICML 2018
On the Model Shrinkage Effect of Gamma Process Edge Partition Models NIPS 2017
Evaluating the Variance of Likelihood-Ratio Gradient Estimators ICML 2017
Averaged Collapsed Variational Bayes Inference JMLR 2017
Expectation Propagation for t-Exponential Family Using q-Algebra NIPS 2017
A Quantum-Inspired Ensemble Method and Quantum-Inspired Forest Regressors ACML 2017
Differential Privacy without Sensitivity NIPS 2016
Approximation Analysis of Stochastic Gradient Langevin Dynamics by using Fokker-Planck Equation and Ito Process ICML 2014
Formalizing Word Sampling for Vocabulary Prediction as Graph-based Active Learning EMNLP 2014
Analysis of Variational Bayesian Latent Dirichlet Allocation: Weaker Sparsity Than MAP NIPS 2014
Latent Confusion Analysis by Normalized Gamma Construction ICML 2014
Understanding seed selection in bootstrapping EMNLP 2013
Multi-armed Bandit Problem with Lock-up Periods ACML 2013
Reducing Wrong Labels in Distant Supervision for Relation Extraction ACL 2012
Mining Words in the Minds of Second Language Learners: Learner-Specific Word Difficulty COLING 2012
Deterministic Single-Pass Algorithm for LDA NIPS 2010
Bayesian Document Generative Model with Explicit Multiple Topics EMNLP 2007
Bayesian Document Generative Model with Explicit Multiple Topics CONLL 2007