論文表記の著者名
Naoki Nishikawa
東京大学Machine Learning2022–2026 LIVE
対象論文 9 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
- Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
- Inference-time Alignment with Rewards in Besov Spaces: Provable Advantages of Feature Learning and Multi-Step Policy Updates
- State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
- Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
- Nonlinear transformers can perform inference-time feature learning
- Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
- From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
- Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds
- Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime