Reading List

This reading list is maintained for personal record. Starting from October, I update more of these content on my Telegram channel. Join this telegram channel for my personal machine learning & data science knowledge sharing if you are interested.

2022 July

1. Modeling Non-linear Least Squares. This one is about Ceres solver.
2. A General and Adaptive Robust Loss Function. This one gives a general form of all sorts of robust loss functions. The github repo can be found here.
3. Conditional Number. This wiki discusses the well-conditioned and ill-conditioned case.
4. A robust hybrid of lasso and ridge regression. This is a paper about huber regression. The sklearn repo can be found here.
5. Exploring Bayesian Optimization. This is a good tutorial for bayesian optimization. But I haven't got time to read another paper about this.
6. GRACGE: Graph Signal Clustering and Multiple Graph Estimation. I encountered this paper in the group meeting this month. The proof utilized many techniques I learnt in SEEM5380 (optimization methods for high-dimensional statistics).
7. Pari-Mutuel Markets: Mechanisms and Performance. This work talks about different mechanisms in the pari-mutuel market. It gives a good explanation for readers to understand how the optimization problem is formulated.
8. Regular expression: I started to use regular expression systematically this month. Here are some useful tutorial webpages for reference.

• Chinese Version Introduction
• English Tutorial
• Python Library
• Kaggle Notebook for python re

9. NGBoost. The idea of natural gradient is quite worth exploration. But I haven't got enough time to read through this paper recently.
10. CatBoost. I started looking at this documentation to see how categorical values are transformed into numerical ones in CatBoost. I plan to read the paper in the near future to further understand the mechanism of this model.
11. Radial Basis Function Network: This topic is waiting to be gone through in the future. Here I only list a few reading sources for self reference later.

• Chinese Tutorial

12. PyTorch: My major plan in terms of coding this summer would be to systematically learn PyTorch framework (and extend to Tensorflow in the future if time allows).

• Official Tutorial
• Chinese Version
• Github Tutorial I
• Github Tutorial II

13. Neural Networks: I came into this video series by 3b1b on Youtube. Chapter 4 provides a good explanation of back propagation. And here is a introduction article for the idea of momentum in SGD.

2022 August

1. Python Set Operation. I reviewed all the set operation based on this this article.
2. CHINA'S FINANCIAL SYSTEM AND ECONOMY: A REVIEW. This article gives a systematical review for the financial system in China. I am typically interested in the bond market insights.
3. Coupon Collector Problem.

2022 September

1. Manifold Learning
2. Spectral Clustering

A few of the mentioned readings are in this file.

2022 October to November

1. Graph Laplacian and spectrum continued.
2. I began a telegram channel for knowledge about data science.
3. Some market news & newsletter.
4. NLP tasks paper reading.