Keitaro Sakamoto

According to our database, Keitaro Sakamoto authored at least 6 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2026

Locking Pretrained Weights via Deep Low-Rank Residual Distillation.

Keitaro Sakamoto, Pierre Ablin, Federico Danieli, Marco Cuturi

CoRR, May, 2026

2025

Explaining Grokking and Information Bottleneck through Neural Collapse Emergence.

Keitaro Sakamoto, Issei Sato

CoRR, September, 2025

Benign Overfitting in Token Selection of Attention Mechanism.

Keitaro Sakamoto, Issei Sato

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training.

Keitaro Sakamoto, Issei Sato

Trans. Mach. Learn. Res., 2024

Benign or Not-Benign Overfitting in Token Selection of Attention Mechanism.

Keitaro Sakamoto, Issei Sato

CoRR, 2024

2022

Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective.

Keitaro Sakamoto, Issei Sato

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022