Daisuke Yamada

PhD in CS, UW–Madison · 山田大介

Daisuke Yamada

I'm a 3rd year PhD student in Computer Science at the University of Wisconsin–Madison, working with Professor Vikas Singh. I graduated from Carleton College with degrees in Mathematics and Computer Science.

My research is in machine learning, where I aim to develop mathematical foundations for more efficient and reliable AI systems. A recurring theme in my work is exploiting structure: both the geometric and algebraic structure underlying how models represent and compose information, and external structure, such as hierarchies, present in the data itself. I'm interested in how making this structure explicit can lead to more compact, efficient, and interpretable methods in ML.

I'm from Japan. Outside of research, I listen to piano. I also travel often and studied abroad at DIS in Copenhagen, Denmark and Budapest Semesters in Mathematics (BSM) in Hungary.

email · GitHub · LinkedIn
Always happy to chat about research or potential collaborations.

2026

TMLR · NeurIPS (J2C Track) ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
Daisuke Yamada, Harit Vishwakarma, Ramya Korlakai Vinayak
Transactions on Machine Learning ResearcharXiv
ICML Tree-Structured Orthonormal Decomposition of the Aitchison Simplex
Daisuke Yamada, Qijun Zhang, Travis Pence, Barbara Bendlin, Federico Rey, Vikas Singh
International Conference on Machine LearningarXivICML
ICML Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories
Travis Pence, Daisuke Yamada, Vikas Singh
International Conference on Machine LearningarXivICML

2025

NeurIPS Composing Linear Layers from Irreducibles
Travis Pence, Daisuke Yamada, Vikas Singh
Conference on Neural Information Processing SystemsarXivNeurIPS

2024

PUMP Selecting Balls From Urns With Partial Replacement Rules
Julian Burden, Chandramauli Chakraborty, Qizhou Fang, Lisa Lin, Nasser Malibari, Sammi Matoush, Isaiah Milbank, Zahan Parekh, Martín Prado, Rachael Ren, Qizhao Rong, Maximiliano Sánchez Garza, Eli Sun, Enrique Treviño, Daisuke Yamada
PUMP Journal of Undergraduate ResearchPaper

2023

Undergrad Thesis Image-Adaptive Generative Adversarial Networks
Daisuke Yamada · Carleton College, advised by Prof. Anna Rafferty
Carleton CollegePDF