2 papers
cs.LG2025
Feature compression is the root cause of adversarial fragility in neural network classifiers
Jingchao Gao, Ziqing Lu, Raghu Mudumbai +6
In this paper, we uniquely study the adversarial robustness of deep neural networks (NN) for classification tasks against that of optimal classifiers. We look at the smallest magni…
cs.CL2025
Slaves to the Law of Large Numbers: An Asymptotic Equipartition Property for Perplexity in Generative Language Models
Tyler Bell, Avinash Mudireddy, Ivan Johnson-Eversoll +2
We prove a new asymptotic un-equipartition property for the perplexity of long texts generated by a language model and present supporting experimental evidence from open-source mod…