174 citations · 991 across the 46 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 1 cited
On Achieving Optimal Adversarial Test Error
Justin D. Li, Matus Telgarsky
We first elucidate various fundamental properties of optimal adversarial predictors: the structure of optimal adversarial convex predictors in terms of optimal adversarial zero-one…
cs.LG2023★ 13 cited
Representational Strengths and Limitations of Transformers
Clayton Sanford, Daniel Hsu, Matus Telgarsky
Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compar…