ABCDEFGHIJKLMNOPQRSTUVWXYZAA
1
DateClassContentSlidesRequired ReadingExtrasDue2021S LecturesNotes
2
09/091Organization; Context, Motivation, History, and LanguagesL1.pdfL1P2.pdfYouTube Link
add compelling applications, i.e. from crossover.ai talk
3
09/142Introduction to Model-Based ReasoningL2.pdfIntro to Prob. Prog. [Chap. 1]YouTube Link
4
09/163Review - Graphical ModelsL3.pdfessentials-of-bayesian-inference.pdfYouTube link
too short; should actually go into more details about "derivations" of graphical models at end of lecture; could include graphical model properties; at least D-separation explicitly. even simple conditional independence checks would be nice
5
09/214Review - Inference, Learning, Monte Carlo, SamplingL4-5.pdfYouTube linkcan split into two lectures
6
09/235Review - Markov Chain Monte CarloL4-5.pdflda-sampler.pdfDemoYouTube link
should talk about burn-in and trace plots (and require in homeworks)
7
09/286Review - Before prob. prog.; a non-trivial HMM exampleL6.pdfgmm.pdfYouTube link
8
09/307T&R
9
10/058
Graphical Models, First Order Probabilistic Programming Language (FOPPL), and Sugar
L7-8.pdfIntro to Prob. Prog. [Chap. 2]HW 1YouTube link
10
10/079
Graphical Models, First Order Probabilistic Programming Language (FOPPL), and Sugar
L7-8.pdfYouTube link
11
10/1210FOPPL to Graphical Model CompilationL9.pdfIntro to Prob. Prog. [Chap. 3, Sec. 3.1]Project ProposalYouTube link
12
10/1411Graph-Based InferenceL10.pdf
Intro to Prob. Prog. [Chap. 3, Sec. 3.2-3.4,3.6]
YouTube link
13
10/1912Hamiltonian Monte CarloL11.pdf
[1, Chaps. 3.5], https://chi-feng.github.io/mcmc-demo/app.html
DemoHW 2YouTube linkactual due date 10/20
14
10/2113Evaluation-based Inference - Likelihood Weighting, LMH, BBVIL12.pdfIntro to Prob. Prog. [Chap. 4, Sec. 4]YouTube link
probably should do variational inference first; definitely need a slide or two on SGD just to make sure folks know it when it rolls around; there was confusion about the baseline and dimenions in BBVI
15
10/2614Variational Inference L13.pdf
NeurIPS Tutorial Video
HW 3YouTube link
16
10/2815Higher Order Probabilistic Programming Languages (HOPPL)L14.pdfIntro to Prob. Prog. [Chap. 5]YouTube link
17
11/0216SMC - Bootstrap
L15-16.pdf
Intro to Prob. Prog. [Chap. 4, Sec. 3]Chopin LectureYouTube link
18
11/0417SMC - PMMH
L15-16.pdf
Intro to Prob. Prog. [Chap. 6]HOPPL SMC/PMCMCHW 4YouTube link
19
11/0918HOPPL InferenceL17.pdfIntro to Prob. Prog. [Chap. 7, Sec. 1]YouTube link
20
11/1119Midterm breakHW 5
21
11/1620Amortized Inference / Guide Programs / Inference CompilationL18.pdf[1, Chap. 6.1-6.5]YouTube link
22
11/1821Model LearningL19.pdf[1, Chap. 7.1]HW 6YouTube link
23
11/2322Deep Probabilistic ProgrammingL20.pdfLast day to drop with a W (maybe?)YouTube link
24
11/2523Meta-LearningL21.pdf
https://www.overleaf.com/read/knxnpkxnvhdt
YouTube link
the first part being total evidence and the meta-learning objective relationship was not clear
25
11/3024Reinforcement Learning as InferenceL22.pdf
https://www.overleaf.com/read/xkzwqvjtpxjf
YouTube link
26
12/0225Alternative Variational BoundsL23.pdf
https://www.overleaf.com/read/ybdjmjkbrgwy
YouTube link
27
12/0726Reparametrization and Normalizing Flows (guest lecturer: Harvey)L24.pdf
https://www.overleaf.com/read/vhqhnfvnrkzj
YouTube link
28
GANs and Adversarially Learned Inference (guest lecturer: Munk)L25.pdf
https://www.overleaf.com/read/vxkzyxysdvvc
YouTube link
29
30
TBDFinal Project Presentations; In person whenever it happensReports due 12/22 midnight.
31
32
Extras
33
Automatic differentiation theoryL13[2, Chaps. 1-2]
34
Automatic differentiation implementationL14[2, Chaps. 3-4]
35
Next year
36
Attention and Bayesian Experimental Design
37
Deep Generative Models; Variational RNNs, Deep Non-linear Dynamical Systems Models
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100