Research
My research interests center around the statistical theory of machine learning algorithms, but I use the term "algorithm" broadly, to include the decisions made by the practioner interacting with data and tweaking algorithm code. I like to ask basic research questions that relate to solving learning problems in "hard" settings. In particular, I am interested in situations in which the learning algorithm (and its designer) have limited knowledge of the quality of data or feedback available, especially when our definition of "good performance" is something other than "a small average loss at test time."
In the end, I hope that my work contributes to a machine learning methodology that enable us to reliably design efficient algorithms that work for reasons we understand.
For research papers:
I try to ensure all the work I have published is freely available to the public. Please check out my publications page for details.
For software:
Please see my repositories on GitHub (username: feedbackward).
For a more detailed CV (funding, etc.):
Please see my researchmap page, in either English or Japanese, as you prefer.
For my JST PRESTO (2021-2026) project page
I have a designated page on this site dedicated to my research project funded by JST PRESTO, in which I provide some background information as well as updates regarding progress, papers, software, talks, etc.
