# Hi, I’m Daiki Chijiwa

- Twitter: @dchiji_en
- E-mail: daiki.chijiwa [at] ntt.com

## About

I am a researcher at NTT (Computer and Data Science Laboratories, Japan) since 2019. Previously I majored in Mathematics and studied complex algebraic geometry and Hodge theory during the master’s degree program.

Current research interests: neural networks, meta-learning, statistical learning theory

## Brief CV

- April 2019 - current: Researcher at NTT Corp, inc.
- April 2016 - March 2019: M.S. in Mathematical Sciences, The University of Tokyo
- Master’s thesis: On certain algebraic cycles on abelian varieties of Fermat type.
- Advisor: Tomohide Terasoma

- April 2012 - March 2016: B.S. in Mathematics, Tokyo Institute of Technology
- Advisor: Shouhei Ma

## Publications

### Preprints

- M. Yamada, T. Yamashita, S. Yamaguchi,
__D. Chijiwa__, Revisiting Permutation Symmetry for Merging Models between Different Datasets, arXiv:2306.05641 - D. Chijiwa, Transferring Learning Trajectories of Neural Networks [animation], arXiv:2305.14122
- S. Yamaguchi, S. Kanai, A. Kumagai,
__D. Chijiwa__, H. Kashima, Transfer Learning with Pre-trained Conditional Generative Models, arXiv:2204.12833

### Journals / International Conferences

- S. Yamaguchi,
__D. Chijiwa__, S. Kanai, A. Kumagai, H. Kashima, Regularizing Neural Networks with Meta-Learning Generative Models, Advances in Neural Information Processing Systems (**NeurIPS**), 2023 __D. Chijiwa__, S. Yamaguchi, A. Kumagai, Y. Ida, Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks, Advances in Neural Information Processing Systems (**NeurIPS**), 2022__D. Chijiwa__, S. Yamaguchi, Y. Ida, K. Umakoshi, T. Inoue, Pruning randomly initialized neural networks with iterative randomization, Advances in Neural Information Processing Systems (**NeurIPS**, selected as**Spotlight**), 2021

### Non-archival Workshops

- S. Yamaguchi, D. Chijiwa, S. Kanai, A. Kumagai, H. Kashima, Regularizing Neural Networks with Meta-Learning Generative Models, Data-centric Machine Learning Research (DMLR) Workshop (ICML 2023, Honolulu, Hawaii)
- D. Chijiwa, On the Problem of Transferring Learning Trajectories Between Neural Networks, Workshop on High-dimensional Learning Dynamics (ICML 2023, Honolulu, Hawaii)

### Master’s Thesis

__D. Chijiwa__, On certain algebraic cycles on abelian varieties of Fermat type, 2019.