Author

T. C. Johnson

h-index 1 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Adversarial Training Without Input Gradients via Low-Rank Householder Expansions

That such a regularizer exists is the main finding: the methods that dispense with the inner search all obtain their local geometry by differentiating with respect to the input, and it is shown this is not necessary.

T. C. Johnson, Donsub Rim · 0 citations