3 papers
cs.LG2026
Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing
Anxin Guo, Jingwei Li
Large language models often hallucinate with high confidence on "random facts" that lack inferable patterns. We formalize the memorization of such facts as a membership testing pro…
cs.LG2024
Agnostic Learning of Arbitrary ReLU Activation under Gaussian Marginals
Anxin Guo, Aravindan Vijayaraghavan
We consider the problem of learning an arbitrarily-biased ReLU activation (or neuron) over Gaussian marginals with the squared loss objective. Despite the ReLU neuron being the bas…
cs.DS2024
To Store or Not to Store: a graph theoretical approach for Dataset Versioning
Anxin Guo, Jingwei Li, Pattara Sukprasert +3
In this work, we study the cost efficient data versioning problem, where the goal is to optimize the storage and reconstruction (retrieval) costs of data versions, given a graph of…