| Office hours | |||
|---|---|---|---|
| Instructor | Mikhail Traskin | mtraskin@wharton | Tuesday/Thursday, 10:30 am – 12:00 pm, 466 Jon M. Huntsman Hall |
G90 Jon M. Huntsman Hall. Tuesday/Thursday, 1:30 – 3:00 pm.
Refer to http://stat.wharton.upenn.edu/~mtraskin/courses/stat553/spring08/index.html (this page) for announcements, handouts, homework assignments and other materials.
This course gives a broad overview of the machine learning and statistical pattern recognition. Some topics will be rather glanced over while others will be considered in-depth. Topics include supervised learning (generative/discriminative models, parametric/nonparametric, neural networks, support vector machines, boosting, bagging, random forests), online learning (prediction with expert advice), learning theory (VC dimension, generalization bounds, bias/variance trade-off), unsupervised learning (clustering, k-means, PCA, ICA). Most of the course concentrates on the supervised learning and on online learning. [More details]
Assignments will be due at the class three lectures after being passed out. Late homeworks will not be accepted.
There will be a final project in an area relevant to the course. Feel free to discuss topics with me, or ask for suggestions. Project proposals are due March 18 (one or two paragraphs in an email message to mtraskin at wharton). Project reports are due April 29. We will have project poster presentations on April 29.
Amit Agarwal, Elad Hazan, Satyen Kale and Robert E. Schapire (2006). Algorithms for portfolio management based on the Newton method. In Proceedings of 23rd International Conference on Machine Learning.
Amit Agarwal, Elad Hazan and Satyen Kale (2007). Logarithmic Regret Algorithms for Online Convex Optimization. Machine Learning, vol. 69, no. 2-3, 169–192 (December 2007).
Avrim Blum and Adam Kalai (1999). Universal portfolios with and without transaction costs. Machine Learning, vol. 35, no. 3, pp. 193–205.
Thomas Cover (1991). Universal portfolios. Mathematical finance, 1, 1–19.