Albert No

Rate-Distortion Theoretic Model Compression: Successive Refinement for Pruning

2021 · arXiv (Cornell University)

We study the neural network (NN) compression problem, viewing the tension between the compression ratio and NN performance through the lens of rate-distortion theory. We choose a distortion metric that reflects the effect of NN …

SEPS: A Separability Measure for Robust Unlearning in LLMs

2025 · arXiv (Cornell University)

Machine unlearning aims to selectively remove targeted knowledge from Large Language Models (LLMs), ensuring they forget specified content while retaining essential information. Existing unlearning metrics assess whether a model correctly answers retain queries and rejects …