Machine Learning

By Yinggan XU Dibbla The tutorial video can be found here This notebook will only cover the basic optimizers and their ideas. However, the optimizers for DL remains a very interesting question. Background Knowledge $\mu$-strong Convexity We can refer to this note. A function $f$ is $\mu$-strong convex if: $$f(y)\ge f(x)+\nabla f(x)^T(y-x) + \frac{\mu}{2}||y-x||^2\newline \text{for some $\mu\ge0$ and for all $x,y$}$$ Note that Strong convexity doesn’t necessarily require the function to be differentiable, and the gradient is replaced by the sub-gradient when the function is non-smooth....

By Yinggan XU Dibbla In this Lecture, Lee introduces the idea of select best model through validation set performance. Lee also explains how deep NN outperforms fat (wide) NN. Validation set The CORE question we want to figure out is Why I used validation set but still overfit? graph LR id1[model 1 with para space H1] id2[model 2 with para space H2] id3[model 3 with para space H3] id4[Validation Set] id1-->id4 id2-->id4 id3-->id4 id5[Validation-Loss-1=0....

By Yinggan XU Dibbla The notebook basically is a summary for what is mentioned in Hung-Yi Lee’s ML course 2022. Sometimes people have contradictive ideas like whether PPO is an off-policy algorithm (or my grammar mistakes in the notebook) , but in this notebook, I’m going to make things aligned with Hung-Yi Lee’s idea. Lecture 1 - Intro & Basic Idea of ML The basic idea of ML, according to Lee, is to find a function....