Printable PDF
Department of Mathematics,
Department of Mathematics,
University of California San Diego
****************************
Prof. Rayan Saab
UCSD
Compressing neural networks: sparsity, quantization, and low-rank approximation
Abstract:
We will discuss recent advances in the compression of pre-trained neural networks using both novel and existing computationally efficient algorithms. The approaches we consider leverage sparsity, low-rank approximations of weight matrices, and weight quantization to achieve significant reductions in model size, while maintaining performance. We provide rigorous theoretical error guarantees as well as numerical experiments.
May 21, 2025
4:00 PM
APM 6402 & Zoom (Meeting ID: 941 4642 0185 / Password: 278C2025)
Research Areas
Optimization****************************
