250MLS: Fall 2016: List of Sources
[B] Pattern Recognition and Machine Learning, by C. M. Bishop,
[M] Machine Learning: A Probabilistic Perspective, by Kevin P. Murphy,
MIT Press, 2012.
Graphical Models, Exponential Families, and Variational Inference,
J. Wainwright and M. I. Jordan, 2008.
Probabilistic Graphical Models, D. Koller and N. Friedman, 2009.
Gaussian Processes for Machine Learning, Carl Edward Rasmussen and Chris Williams, 2006
- 9/7; 9/12
An Introduction to Variational Methods
for Graphical Models, Jordan et al, 1999.
Variational inference Slides
Probabilistic Topic Models,
Steyvers & Griffiths, 2007
Latent Dirichlet allocation, D. Blei, A. Ng, and M. Jordan, 2003.
Dirichlet process review, Y.W. Teh
Variational inference for Dirichlet process mixtures.
D. Blei and M. Jordan.
Dirichlet Process slides
- 9/21; 9/26; 9/28 Presentations
- 9/28; 10/5
- Graphical models (directed, undirected and
factor graphs) and Belief Propagation
- [AIMA],[B] chapter 8, [KF] chapters 9-10, [M] chapter 20.
Recursive version of BP for directed case from
Russell and Norvig, 1995 (1st edition).
BP slides part 1
BP slides part 2
- 10/3; 10/10; 10/12 no class
- 10/17, 10/19
- EP [B]
Minka's Thesis (pages 13-26)
EP for GP: [RW] sections 3.6, 3.9
EP slides part 1
EP slides part 2
Not covered but for reference:
- 10/24, 10/26
- Exponential family distributions and their connection to covex
duality and graphical models: [WJ] Chapter 3.
Exp family slides
- 10/31, 11/2
- Variational, BP, EP as "variational optimization": [M] Section
22.3, [WJ] Chapters 4, 5, 7.
Unifying Variational Inference slides
11/7: Planning and inference:
Factorial Hidden Markov Models
Variational methods for Reinforcement Learning
11/9: Generic Methods for Variational Inference:
Stochastic Variational Inference
11/14: Generic Methods for Variational Inference:
Black Box Variational Inference
Black-Box Stochastic Variational Inference
in Five Lines of Python
11/16: Planning and inference:
Variational Algorithms for Marginal MAP
Variational Planning for Graph-based MDPs
11/21: Generic Methods for Variational Inference:
Variational Message Passing
11/28 Overview of Deep networks and
Deep Residual Learning for Image Recognition
Going Deeper with Convolutions
Very Deep Convolutional Networks for Large-Scale Image Recognition
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
11/30: Bayesian Models and Deep learning:
Auto-Encoding Variational Bayes
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
12/5: Bayesian Models and Deep learning:
Variational Dropout and the Local Reparameterization Trick
12/7: Bayesian Models and Deep learning:
Identity Matters in Deep Learning
12/12: Bayesian Models and Deep learning:
Variational Inference with Normalizing Flows