ABCDEFGHIJKLMNOPQRSTU
1
9.520: Statistical Learning Theory and Applications - Fall 2015 (Project Examples)
2
WIKIPEDIA (complete/done): http://www.mit.edu/~9.520/fall15/9520_wikipedia_projects_list.pdf
3
4
5
WIKIPEDIA entries (partially done, not submitted)
6
Lasso Regression : https://en.wikipedia.org/wiki/User:Rezamohammadighazi/sandbox
7
8
Regularized Least Squares : https://en.wikipedia.org/wiki/User:Yakirrr
9
Error Tolerance (PAC Learning): https://en.wikipedia.org/wiki/User:Alex_e_e_alex/sandbox
10
Density Estimation : https://en.wikipedia.org/wiki/User:Linjing1119/sandbox
11
Matrix Completion : https://en.wikipedia.org/wiki/User:Milanambiar/sandbox
12
Multiple Instance Learning : we have Wiki markup
13
Uniform Stability and Generalization in Learning Theory: https://en.wikipedia.org/wiki/Draft:Uniform_Stability_and_Generalization_in_learning_theory
14
Generalization Error: https://en.wikipedia.org/wiki/User:Agkonings/sandbox
15
Structured Sparsity Regularization : https://en.wikipedia.org/wiki/User:A.n.campero/sandbox
16
Proximal Operator for Matrix Function: https://en.wikipedia.org/wiki/User:Lovebeloved/sandbox
17
Sparse Dictionary Learning: (pdf -- no sandbox available)
18
PAC Learning : https://en.wikipedia.org/wiki/User:Scott.linderman/sandbox
19
Convolutional Neural Networks : https://en.wikipedia.org/wiki/User:Wfwhitney/sandbox
20
Frames/Basis Functions: https://en.wikipedia.org/wiki/Frame_(linear_algebra)
21
22
Large Scale Learning
23
Nystrom, Random Features
24
SVM derivation through Subgradient Descend on regularized hinge loss
25
26
GURLS/Coding/Implementations
27
MATLAB
28
Lasso & Elastic Net
29
Matching pursuit and Orthogonal Matching Pursuit
30
Semi-supervised with Graph Laplacian
31
(Overlapping) Group Sparsity
32
Logistic (w. Landweber/Early Stopping)
33
SubG SVM
34
ISTA/FISTA
35
MKL (L1 or L2, combination and or selection)
36
Non-linear Variable Selection (through MKL)
37
KPCA (and PCA)
38
Nystrom
39
Non-MATLAB
40
- Python wrapper: https://github.com/phrqas/GURLS
41
- Julia porting: https://github.com/joehuchette/GURLS.jl
42
- …
43
various
44
- Stat. permutation tests (?)
45
- GUI (?)
46
- Visualization techniques/Representation (?)
47
- Benchmarks with other packages (time, performance)
48
49
50
Exercises
51
1. Statistical Learning Theory
52
2. Foundational Results/Stability/Generalization
53
3. Hypothesis Spaces
54
4. Regularization Networks
55
5. Regularization: Beyond Penalization
56
6. Sparsity, Low Rank ...
57
7. Manifold Regularization
58
8. Data representation Learning
59
Optimization
60
Generalization Bounds, Stability
61
Regularization parameter choice: theory and practice
62
Regularization with Multiple Kernel Learning
63
Online Learning
64
Deep learning theory
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