4 papers
When a Flatness Proxy Is Not a Function: Robustness Certificates and Training Interventions
Vicente Opazo, Jose Calatayud-Mateu, Cristobal Rojas +1
A valid curvature upper bound need not justify either a robustness certificate or an intervention on an intrinsic predictor property. We demonstrate this distinction for a last-lay…
Three Tokens Force Exponential Feature Rank in Nonnegative Kernel Attention
Vicente Opazo
How much feature rank does comparison require in kernel attention? On Min-IP over -bit tokens, rank one solves every sequence of length at most two exactly. At length three, the…
Indexing: the Beginning and the End
Alexander Kozachinskiy, Vicente Opazo, Felipe Urrutia
We study information bottlenecks in modern deep-learning architectures -- RNNs, softmax transformers, linear-attention transformers and state-space models -- through the lens of th…
Polynomial-Time Mistake-Bounded Language Generation
Héctor Jimenez, Alexander Kozachinskiy, Vicente Opazo
In this paper, we introduce a polynomial-time version of the mistake-bounded language generation (MBLG) framework due to Kleinberg, Peale, and Reingold (2026). We obtain upper and…