論文表記の著者名
Issei Sato
東京大学Machine Learning2021–2025 確定版
対象論文 19 本
著者名は論文に記載された表記をそのまま使用しており、同一人物の名寄せは行っていません。
印刷日： 全論文
論文上の著者表記・公開時所属による集計です。人物の名寄せ・現在所属・全業績を表すものではありません。
対象論文
論文一覧
- Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment
- On the Optimal Memorization Capacity of Transformers
- Benign Overfitting in Token Selection of Attention Mechanism
- On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
- Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
- Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
- Exploring Weight Balancing on Long-Tailed Recognition Problem
- Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
- Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
- Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
- On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
- Disentanglement Analysis with Partial Information Decomposition
- Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
- A Closer Look at Prototype Classifier for Few-shot Image Classification
- Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective
- A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima
- Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
- Loss function based second-order Jensen inequality and its application to particle variational inference
- Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning