Satoki Ishikawa

According to our database, Satoki Ishikawa authored at least 6 papers between 2023 and 2024.

Collaborative distances:

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

2024

Lion Cub: Minimizing Communication Overhead in Distributed Lion.

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

CoRR, 2024

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

Satoki Ishikawa, Rio Yokota, Ryo Karakida

CoRR, 2024

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

Satoki Ishikawa, Makoto Yamada, Han Bao, Yuki Takezawa

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