Takumi Nakagawa

According to our database, Takumi Nakagawa authored at least 5 papers between 2022 and 2024.

Collaborative distances:

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

2024

Denoising cosine similarity: A theory-driven approach for efficient representation learning.

Takumi Nakagawa, Yutaro Sanada, Hiroki Waida, Yuhui Zhang, Yuichiro Wada, Kosaku Takanashi, Tomonori Yamada, Takafumi Kanamori

Neural Networks, January, 2024

Scaling-based Data Augmentation for Generative Models and its Theoretical Extension.

Yoshitaka Koike, Takumi Nakagawa, Hiroki Waida, Takafumi Kanamori

CoRR, 2024

Robust VAEs via Generating Process of Noise Augmented Data.

Hiroo Irobe, Wataru Aoki, Kimihiro Yamazaki, Yuhui Zhang, Takumi Nakagawa, Hiroki Waida, Yuichiro Wada, Takafumi Kanamori

Proceedings of the IEEE International Symposium on Information Theory, 2024

2023

Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis.

Hiroki Waida, Yuichiro Wada, Léo Andéol, Takumi Nakagawa, Yuhui Zhang, Takafumi Kanamori

Proceedings of the Machine Learning and Knowledge Discovery in Databases: Research Track, 2023

2022

Deep Self-Supervised Learning of Speech Denoising from Noisy Speeches.

Yutaro Sanada, Takumi Nakagawa, Yuichiro Wada, Kosaku Takanashi, Yuhui Zhang, Kiichi Tokuyama, Takafumi Kanamori, Tomonori Yamada

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022