Satoki Ishikawa

According to our database, Satoki Ishikawa authored at least 8 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks.

Taishi Nakamura, Satoki Ishikawa, Masaki Kawamura, Takumi Okamoto, Daisuke Nohara, Jun Suzuki, Rio Yokota

CoRR, August, 2025

PhiNet v2: A Mask-Free Brain-Inspired Vision Foundation Model from Video.

Makoto Yamada, Kian Ming A. Chai, Ayoub Rhim, Satoki Ishikawa, Mohammad Sabokrou, Yao-Hung Hubert Tsai

CoRR, May, 2025

Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation.

Satoki Ishikawa, Rio Yokota, Ryo Karakida

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis.

Satoki Ishikawa, Makoto Yamada, Han Bao, Yuki Takezawa

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Lion Cub: Minimizing Communication Overhead in Distributed Lion.

Satoki Ishikawa, Tal Ben-Nun, Brian Van Essen, Rio Yokota, Nikoli Dryden

CoRR, 2024

When Does Second-Order Optimization Speed Up Training?

Satoki Ishikawa, Rio Yokota

Proceedings of the Second Tiny Papers Track at ICLR 2024, 2024

On the Parameterization of Second-Order Optimization Effective towards the Infinite Width.

Satoki Ishikawa, Ryo Karakida

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

ASDL: A Unified Interface for Gradient Preconditioning in PyTorch.

Kazuki Osawa, Satoki Ishikawa, Rio Yokota, Shigang Li, Torsten Hoefler

CoRR, 2023