Dropout as Implicit Bagging
March 7, 2026
Chapter 7 clarified that dropout works so well because it approximates bagging over many thinned networks with shared parameters.
Read article2 posts currently filed under ML Theory.
Chapter 7 clarified that dropout works so well because it approximates bagging over many thinned networks with shared parameters.
Read article
Chapter 6 sharpened how I think about architecture as a structural assumption, not just a tuning choice.
Read articleCopyright © 2020 - 2026 Alex Leung