Welcome to Math 6040/7260: Linear Models. Here is some essential information to get started with Math 6040/7260.

Class webpage

Please bookmark and visit the course webpage frequently for the most updated information: https://tulane-math-7260-2023.github.io/.

Lecture format

With the COVID-19 pandemic going on, the lectures will be delivered in a hybrid mode. Exams will be take-home to accommodate any future uncertainties.

I will deliver lectures at Gibson Hall 126 and Zoom https://tulane.zoom.us/j/91380486474 on Mondays, Wednesdays and Fridays (Mon/Wed/Fri 9:00am-9:50am). Friday classes will consist a mixture of lectures (first 2/3 weeks) and practical lab sessions. Lectures will include presentation slides and questions.

Attendance

I do require attendance. However, you could attend classes through any of the following format

  1. In person (Monday / Wednesday / Friday)
  2. Watching zoom recordings

Grades

There will be one mid-term and one final exam. There will be roughly 4 sets of homework problems.

All graduate students are required to deliver a 15-min talk (10 min presentation + 5 min questions) on one of the following topics (secure yours before others do). You may suggest a topic outside of the pool too. Undergraduate students are encouraged to participate too with bonus 5 points towards the final score.

  Math-6040 Math-7260
Homework 40% 30%
Mid-term exam 30% 30%
Final exam 30% 30%
Presentation 5% (bonus) 10%

Topic pools

The topics are given by key words only. Please practice your ability of “educated” searches with google.

  • Software key words: stan, bugs & jags, hadoop, spark, tensorflow, Scikit-Learn, Blas & Lapack
  • Stastician key words: Harold Hotelling, Joseph Leo Doob, Bradley Efron, Abraham Wald, William Cochran, Sheldon M. Ross, Emile Borel
  • Research areas: Bayesian Statistics, Approximate Bayesian Computation, Sequential Monte Carlo method, Variational Bayes, Spatial statistics
  • Method key words: Gradient descent algorithm, Fast Fourier transform algorithm, Expectation-maximization algorithm, Metropolis-Hastings algorithm, Markov-chain Monte Carlo, Hamiltonian Monte Carlo, Hidden Markov Models, Genome-wide Association Studies,
  • Parallel computing: OpenCL, Cuda, SIMD (SSE + AVX)
  • Other: COPSS Presidents’ Award, International Prize in Statistics