AI RESEARCH

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

arXiv CS.LG

ArXi:2606.02608v1 Announce Type: new We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets. The main practical contribution is accuracy retention under short calibration and fine-tuning schedules, rather than a long post-pruning reoptimization pipeline.