| 
Instructor:
  Dan Gildea 
 Homework
 Required text: Boyd and Vanderberghe, Convex Optimization
 
In addition to this text, we will cover additional numerical
methods taken from Nocedal and Wright and Numerical Recipes. The
second half of the course will focus on applications of
optimization in the context of machine learning.
 
| Tu 1/21 | Intro | Boyd ch 1 |  | Th 1/23 | Convex Sets | Boyd ch 2 |  | Tu 1/28 | Convex Functions | Boyd ch 3 |  | Th 1/30 | Convex Optimization Problems | Boyd ch 4 |  | Tu 2/4 | Convex Optimization Problems | Boyd ch 4 |  | Th 2/6 | Duality | Boyd ch 5 |  | Tu 2/11 | Duality | Boyd ch 5 |  | Th 2/13 | Duality | Boyd ch 5 |  | Tu 2/18 | Approximation | Boyd ch 6 |  | Th 2/20 | Statistical Estimation | Boyd ch 7 |  | Tu 2/25 | Geometric Problems | Boyd ch 8 |  | Th 2/27 | Unconstrained Minimization | Boyd ch 9 |  | Tu 3/4 | Equality Constrained Minimization | Boyd ch 10 |  | Th 3/6 | Interior Point Methods | Boyd ch 11 |  | Tu 3/18 | Interior Point Methods (Arvin) | Boyd ch 11 |  | Th 3/20 | BFGS (Shunzhi) | Nocedal ch 8 |  | Tu 3/25 | Simulated Annealing (Matt) | Kirkpatrick |  | Th 3/27 | Deterministic Annealing (Shunzhi) | Rose |  | Tu 4/1 | Numerical Methods (Matt) | Press 10.4 - 10.6 |  | Th 4/3 | Integer Programming (Aidan) | Nemhauser ch II.4 |  | Tu 4/8 | AdaGrad | Duchi |  | Th 4/10 | The Marginal Value of Adaptive Gradient Methods in Machine Learning (Arvin) | Wilson et el. (2017) |  | Tu 4/15 | no class |  |  | Th 4/17 | training transformers | Kunster ICLR 2023 |  | Tu 4/22 | Graphical Models (Aidan) | Wainwright and Jordan ch 3 |  | Th 4/24 | Graphical Models cont'd | Wainwright and Jordan ch 4 |  | Tu 4/29 | Project Presentations |  | Th 5/1 | Project Presentations |  
Projects due: 5pm Friday 5/2
 GradingStudents will have written assignments, present two lectures,
and complete a final project.
Homework: 30%
Lectures and participation: 30%
Final project: 40%
 gildea @ cs rochester edu
       
       April 21, 2025
 |