Date Topic Subject Book Code
1-21 Classical problems Introduction; problems with classical methods 1.1-1.5 R
1-23 Large scale testing Family-wise error rates R
1-28 Large scale testing False discovery rates R
1-30 Large scale testing Local false discovery rates R
2-04 Large scale testing Hierarchical models and shrinkage R
2-06 Ridge regression Ridge regression 1.6.1-1.6.3 R
2-11 Ridge regression Selection of λ; case studies 1.6.4-1.6.6 R
2-13 Lasso KKT conditions, soft thresholding 2.1-2.2 R
2-18 Lasso (cont’d)
2-20 Lasso Algorithms 2.3-2.4 R
2-25 Lasso Cross-validaton 2.5-2.6 R
2-27 Lasso Case studies, Bayesian interpretation 2.7-2.9 R
3-04 Bias reduction Adaptive lasso, MCP, and SCAD 3.1-3.2 R
3-06 Bias reduction Algorithms and case studies 3.5-3.8 R
3-11 Stability Elastic Net 4.1-4.2 R
3-13 Stability Algorithms; case studies 4.3-4.5 R
3-18 No class; spring break
3-20 No class; spring break
3-25 Theory Theoretical properties 5
3-27 Theory Theoretical properties: Non-asymptotic 5 R
4-01 Theory (cont’d)
4-03 Inference Marginal false discovery rates 6 R
4-08 Inference Debiasing and subsampling/resampling 7, 9 R
4-10 Inference Selective inference R
4-15 Inference Knockoff filter R
4-17 Other likelihoods Logistic regression 10 R
4-22 Other likelihoods Other likelihoods 11-12 R
4-24 Structured sparsity Group lasso 13 R
4-29 Structured sparsity Bi-level selection 14 R
5-01 Structured sparsity Interactions R
5-06 Structured sparsity Fusion penalties 15 R
5-08 Structured sparsity Further applications of penalization and sparsity R
5-12 Final projects 10:00-12:00 in the Biostat Conference Room