**Announcements**
- The FINAL exam will be Savery 168 10:30--12:20
- Previous exams and solutions are here

**What will the course be about?**

- Optimization and convexity in ML, relationship with regularization, compressed sensing, [submodularity]
- Exponential family models and concepts of information theory
- Learning with structured data: mainly graphs and networks, but
possibly orderings, structured prediction, and related
combinatorial-continuous learning tasks.
- [Graphical models and variational inference (if there is time and interest)]

These topics are related by a few underlying major concepts:
convexity, sparsity, conditional independence. These concepts permeate
most of the automated learning tasks of today.
The class will highlight the intimate connection between statistics
and computation (meaning algorithms, data structures, and
optimization) in modeling large or high-dimensional data.
The time and weight of the above topics receive will be decided with
input from the students taking the class.
**Who is this class for?**

This class is a core class in the Machine Learning/Big Data PhD Track in Statistics. For any Statistics student who wants to learn Machine Learning/Big Data and has taken STAT 535 or CSE 546.

STAT 538 class is part of the Machine Learning/Big Data PhD track. For
a bigger picture of the ML/BD classes offered at UW, see this
page.
Capacity permitting, the class is open to other graduate students with
an interest in statistics, algorithms and computing.

**Textbook** No required textbook.

The grade is based (approximately) on **homework + quizzes (%),
miniproject or midterm (%), final exam (%) and class participation
(%).**, with the weights to be decided shortly. The homework will
contain both problems and implementation assignements. The project
will consist of implementation, write-up and short oral
presentation. The final exam will be in class, at the date fixed by
the university, no electronics, 6 pages of notes allowed.

**Prerequisites**

- STAT 535/CSE 546 Foundations of Machine Learning
- Medium ability with a computer programming language (like C, C++, Java or Matlab, Splus, R) at the level of STAT 534

** Instructor:** Marina Meila
mmp at stat dot washington dot edu

** TA** Amit Meir amitmeir at the same domain as mmp

**Lectures**: Tuesdays,10:30 - 11:50 & Thursdays 11:30:12:50 in **Savery 155**

**Office hours:** Monday 2-3pm in PDL B-321

**TA Office hours:** Thursday 15:30-16:30 PDL B-302B

**Recitation:** TBD

**Course home page: **http://www.stat.washington.edu/courses/stat538/winter15 (this page)