Electrical Engineering 227C

Title Optimization for Modern Data Analysis
Description This course will explore theory and algorithms for nonlinear optimization. We will focus on problems that arise in machine learning and computational statistics, paying close attention to concerns about complexity, scaling, and implementation in these domains. Whenever possible, methods will be linked to particular application examples in data analysis. Topics will include Descent algorithms and line search methods Acceleration, momentum, and conjugate gradients Oracle complexity of optimization Newton and Quasi-Newton methods Coordinate descent Stochastic and incremental gradient methods Derivative-free optimization Subgradient calculus and algorithms The proximal point method Projected gradient descent Lagrangian decomposition The Alternating Direction Method of Multipliers
Sections Instructor Teaching Effectiveness How worthwhile was this course?
Spring 2016 Ben Recht 6.3 / 7 6.2 / 7
Spring 2015 Ben Recht 6.3 / 7 6.5 / 7
Spring 2014 Ben Recht 6.0 / 7 6.2 / 7
Overall Rating Teaching Effectiveness How worthwhile was this course?
6.2 / 7 6.3 / 7
[Email HKN about this data] [Info about this page]