Knowledge is everywhere. Let’s share!
While I try to carefully prepare all materials, I might make mistakes. Please feel free to reach out if you spot an error or a doubtful statement in my posts.
I started a series of Stats/ML tutorials at our lab meeting to discuss some topics in statistics and machine learning that are commonly seen in biological applications. My goal is to give a presentation of each topic at a high level and also discuss practical considerations for using the involved methods. In general, the target readers are students without strong Stats/ML background but with some experience in using these methods.
[Feature Selection – pt. I]: Wrapper methods & penalization methods.
[Feature Selection – pt. II]: Penalization methods (cont.).
[R’s C Interface]: Call C functions from R & build an R package with C backend code.
Convex optimization lectures
Convex optimization techniques play an important rule in my research. I took Professor Patrick Combettes’s course, Convex Optimization Methods in Data Sciences, when I was a Ph.D. student at NCSU. My research benefits a lot from that course, and I review my class notes quite often to remind me of some technical details. To help myself understand them deeper, I decided to document my notes into lectures and shared them here. I may reorganize some lectures, include some examples (particularly those I met in my research), and incorporate my own understanding. For more technical details, please refer to his book Convex Analysis and Monotone Operator Theory in Hilbert Spaces. But I am happy to discuss any questions/comments. Shot me an email if you would like to discuss.
[Lecture 1 ]: Euclidean space, related concepts and inequalities.
[Lecture 2 ]: Convex sets and convexity-preserving operations.
[Lecture 3 ]: Nonexpansiveness and its variantss.
- [CUTEst installation and MATLAB interface]: Instructions on installing CUTEst on Linux and using it in MATLAB.