Media Summary: Hope you will enjoy this video. I know my voiceover is lacking some emotion but i will try my best to improve that for my next video. Gradient Descent (unconstrained optima of differentiable function) Note: sound cuts out for last 20 minutes or so, sorry!
First Order Methods Subgradient Projected - Detailed Analysis & Overview
Hope you will enjoy this video. I know my voiceover is lacking some emotion but i will try my best to improve that for my next video. Gradient Descent (unconstrained optima of differentiable function) Note: sound cuts out for last 20 minutes or so, sorry! In this video we start looking at non-smooth optimization. We take a look at the Neither the lasso nor the SVM objective function is differentiable, and we had to do some work for each to optimize with ... So we can define subgrading descent like before we just replace the gradient by
This is a recorded lecture for the graduate-level course on convex optimization offered at UCSB Computer Science Department. Trainable Projected Gradient Method for Robust Fine-tuning CVPR2023