Machine Learning Summer School (MLSS), Cambridge 2009

Approximate Inference

author: Tom Minka, Microsoft Research
published: Nov. 2, 2009, recorded: August 2009, views: 5401

Slides

Slides
0:00	Approximate Inference; Part 1 of 2
0:35	Bayesian paradigm - 1
2:38	Bayesian paradigm - 2
3:11	Factor graphs - 1
5:09	Example factor graph
7:40	Two tasks
8:15	A (seemingly) intractable problem
8:28	Clutter problem
11:25	Exact posterior
13:09	Representing posterior distributions
14:45	Deterministic approximation
15:45	Moment matching
16:32	Today ; Tomorrow
16:38	Best Gaussian by moment matching
17:21	Strategy
19:58	Approximating a single factor
19:59	Graph - 1
21:10	Graph - 2
25:04	Single factor with Gaussian context
32:16	Gaussian multiplication formula
34:03	Approximation with narrow context
37:32	Approximation with medium context
38:03	Approximation with wide context
41:48	Two factors
45:59	Three factors
48:17	Message Passing = Distributed Optimization
52:04	Gaussian found by EP
52:49	Other methods
53:17	Accuracy
55:16	Cost vs. accuracy
62:14	Censoring example
66:29	Time series problems
66:37	Example: Tracking
67:07	Factor graph - 2
68:20	Approximate factor graph
72:25	Splitting a pairwise factor
73:42	Splitting in context
80:43	Sweeping through the graph - 1
81:04	Sweeping through the graph - 2
81:20	Sweeping through the graph - 3
81:28	Sweeping through the graph - 4
83:31	Example: Poisson tracking
84:41	Poisson tracking model
85:07	Factor graph - 3
86:08	Approximating a measurement factor
87:52	Graph - 3
89:37	Graph - 4
90:25	Graph - 5
93:42	Graph - 6

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.