Mathematics of Big Data

Notice

1) Each homework has both pdf and tex versions. To have the tex files successfully compiled, make sure that you have downloaded both macros.tex and hmcpset.cls and put them and the hw tex file under same folder.
If you have any questions with regard to the compilation of the tex files, feel free to ask the grutors for help.

2) For each coding problem, please submit your code to GitHub; please print out any graph or printing statements and submit them with the written part.

3) Solution to every homework is always available. You should try to work on the problems youself before consulting the solution. If you do decide to consult the solution then write a line on the top of your submission saying so, in accordance with the Honor Code.

HOMEWORK

HW Description Starter Files Solution
Homework 1 (pdf)
Homework 1 (tex)
HW1 Files HW1 Solution
Homework 2 (pdf)
Homework 2 (tex)
HW2 Files HW2 Solution
Homework 3 (pdf)
Homework 3 (tex)
No starter file for Homework 3 HW3 Solution
Homework 4 (pdf)
Homework 4 (tex)
HW4 Files HW4 Solution
Homework 5 (pdf)
Homework 5 (tex)
No starter file for Homework 5 HW5 Solution
Homework 6 (pdf)
Homework 6 (tex)
HW6 Files HW6 Solution
Homework 7 (pdf)
Homework 7 (tex)
HW7 Files HW7 Solution
Homework 8 (pdf)
Homework 8 (tex)
HW8 Files HW8 Solution

LECTURE SLIDES

Lecture Numbers Lecture Slides
1 Lecture 1: Overview of Big Data and its Analytics using Linear Regression
2 Lecture 2: Optimization Logistic and Generalized Linear models
3 Lecture 3: Review Probability, Schur Complement, Covariance Matrix and Multivariate Gaussian Distribution
4 Lecture 4: PCA, Dimensionality Reduction, Spectral Decomposition, SVD, Generative Learning Algorithm and Gaussian Discriminant Analysis
5 Lecture 5:Naive Bayes, L1-regularization, Sparsity, Lasso, SVM, and Kernel Method
6 Lecture 6: Unsupervised Learning, K-mean Clustering, Gaussian Mixture, Jensen's inequality and EM
7 Lecture 7: Kernel PCA, One Class SVMs and Learning Theory
8 Lecture 8: Bayesian Learning, Bayesian Logistic and Linear Regressions (review), Bayesian Inference, Intractable Integrals and Motivation for Approximate Methods and Learning Theory
9 Lecture 9: Recommender System, Collaborative Filtering, and Topic Modeling Based on Non-negative Matrix Factorization
Workshop/Additional Materials Workshop: Network Data Modeling

OTHERS