CS 3750 Advanced Topics in Machine Learning
(ISSP 3535)
Time: Tuesday, Thursday
9:30 am - 10:45 am
Location: Sennott Square, Room 5313
Instructor: Milos
Hauskrecht
Computer Science Department
5329 Sennott Square
phone: x4-8845
e-mail: milos_at_cs_pitt_edu
office hours: TBA
Topics and related readings.
Basics of Matrix algebra
Basics of density estimation
- Lecture notes from CS2750
- R.O. Duda, P.E. Hart, D.G. Stork. Pattern
Classification. Second edition. John Wiley and Sons, 2000.
- M. Jordan. Eponential family. In Graphical models. Chapter 7.
- M. Jordan. The Multivariate Gaussian. In Graphical
models. Chapter 12.
Bayesian Belief networks
Complexity Results
- Cooper, G.F., The Computational Complexity of Probabilistic Inference using Bayesian Belief Networks, Artificial Intell., 42, pp. 393-405, 1990.
- Dagum, P. and Luby,M.(1993). Approximating probabilistic
inference in bayesian belief networks is np-hard. Artificial
Intelligence, 60:141--153.
Exact inference algorithms
Monte Carlo methods:
- book by D. Koller and N. Friedman.
- Rubinstein. Simulation and the Monte Carlo Method. 1981.
- David MacKay. Introduction
to Monte Carlo methods.
- Andrieu et al. An introduction to MCMC for Machine Learning. Machine Learning,
vol. 50, pp.5-43, 2003.
-
A brief summary of existing Importance Sampling Algorithms for
Bayesian Networks
- Paul Dagum, Michael Luby.
An Optimal
Approximation Algorithm For Bayesian Inference. Artif
Intelligence, 93:1--27, 1997.
- Jian Cheng, Marek J. Druzdzel.AIS-BN: An
Adaptive Importance Sampling Algorithm for Evidential Reasoning in
Large Bayesian Networks. Journal of Artificial Intelligence Research, 2000.
- Luis E. Ortiz, Leslie Pack Kaelbling. Adaptive
Importance Sampling for Estimation in Structured Domains. In
Proceedings of the UAI 2000, pp. 446-454, 2000.
Loopy Belief propagation
Learning Belief networks from data
Basics:
EM
Component analysis
PCA and SVD
- Lecture notes for CS2750
- Hastie, Tibshirani and Friedman. Elements of statistical
learning. Section 14.5
- Tutorial on PCA
Applications of PCA:
- Link analysis.
- Information Retrieval.
EM algorithms for PCA
Latent Variable Models for
text analysis, information retrieval and link analysis
Probabilistic component analysis
Variational methods
Introduction:
Variational ML learning for component analysis
Variational Bayesian learning:
Other variational learning papers
Kernel methods
Support vector machines (basics):
Kernel methods (basics):
Kernel PCA:
- B. Schokopf, A. Smola, and KR. Muller. Nonlinear Component
Analysis as a Kernel Eigenvalue Problem. Neural Computation 1998. (see
Summary by Ian Fasel)
Kernel ICA:
Various kernels
- String matching:
- Graphs and Discrete structures:
Readings:
Spectral clustering
Last updated by milos
on 08/24/2007