University of Southern California
Machine Learning Center

Class Listing

Introduction

CSCI 567: Machine Learning

Instructor: Yan Liu, Fei Sha

Statistical methods for building intelligent and adaptive systems that improve performance from experiences; Focus on theoretical understanding of these methods and their computational implications.

 

CSCI 573x: Graphical Model

Instructor: Fei Sha, Ram Nevatia

Reasoning under uncertainty, statistical directed and undirected graphical models, temporal modeling, inference in graphical models, parameter learning, decisions under uncertainty. (CSCI 573)

 

EE 588: Optimization for the Information and Data Sciences

Instructor: Mahdi Soltanolkotabi

This course focuses on optimization problems and algorithms that arise in many science and engineering applications. Fundamental topics include convex sets, convex functions, generalized inequalities, least-squares, linear and quadratic programs, semidefinite programming, optimality conditions and duality theory. The course also covers optimization methodology with a focus on first order methods. Sample topics include: efficient first-order algorithms for smooth and non-smooth optimization, accelerated schemes, Newton and quasi-Newton methods, iterative algorithms and non-convex optimization. Some applications to machine learning, statistics, signal processing and control will be presented.

Intermediate

ISE 599: Large Scale Optimization for Machine Learning

Instructor: Meisam Razaviyayn

The objective of the course is to introduce large scale optimization algorithms that arise in modern data science and machine learning applications.

 

CSCI 670: Advance Analysis of Algorithm

Instructor: Shang-Hua Teng

Fundamental techniques for design and analysis of algorithms. Dynamic programming; network flows; theory of NP-completeness; linear programming; approximation, randomized, and online algorithms; basic cryptography.

Advanced

CSCI 686: Advanced Big Data Analytics

Instructor: Yan Liu

Advanced statistical inference and data mining techniques for data analytics, including: topic modeling, structure learning, time-series analysis, learning with less supervision, and massive-scale data analytics.

 

EE 599: Mathematics of High-dimensional Data

Instructor: Mahdi Soltanolkotabi

Modern data sets are noisy and unstructured and often contain corrupted or incomplete information. At the confluence of optimization, signal processing, statistics and computer science a new discipline is emerging to address these challenges. In this course we will explore the foundations of this area. The main goal is to expose students to modern methods that model data through vectors and matrices, efficient algorithms for representing and extracting information from such data as well as new theory explaining the success of these algorithms. A special focus will be on novel methods and mathematical tools that allow us to glean useful information from seemingly incomplete data sets.

 

DSO 607: High-Dimensional Statistics and Big Data Problems

Instructor: Jinchi Lv

Overview of cutting-edge developments of methodologies, theory, and algorithms in high-dimensional statistical learning and big data problems; their applications to business and many other disciplines.