MATH 287D Spring 2013

Department of Mathematics, University of California, San Diego

home | news | research | teaching | misc


    o5:18:13 Homework 3 posted. Due Tuesday 05-30 by 3:00 PM.
    o4:30:13 R code for Lasso posted
    o4:28:13 Reading material for Final Project posted on TED.
    o4:23:13 Homework 2: New due date is Friday 05-03 by 3:00 PM.
    o4:23:13 Homework 2 posted. Due Tuesday 04-30 by 3:00 PM.
    o4:12:13 New reading material on Curses of Dimensionality is posted [pdf]
    o4:11:13 Homework 1 posted. Due Friday 04-19 by 3:00 PM.
    o4:o2:13 Probability and Statistics Day at UCSD Talks
    o4:o2:13 Wednesday lecture o4:o3:13 canceled.
    o4:o1:13 Extension students, please send an email to the instructor to be added to the class email list.
    o4:o1:13 Read the whole page and the syllabus. Download R and familiarize yourself with it.
Fri Apr 12 12:09:57 PST 2013 | archive


    o5:15:13 Empirical risk regularization: finite sample prediction bounds.
    o5:13:13 Surrogate loss functions for classification.
    o5:o6:13 Maximal Margin Classifier, SVM: primal and dual derivation.
    o4:29:13 Clasiffication Methodology and Implementation in R.
    o4:22:13 Rigde, Lasso, Scad and all that fun code. [slides] [R code]
    o4:15:13 Regularization & Shrinkage Methods. [slides]
    o4:10:13 Kernel Methods: Fixed and Stochastic Design.
    o4:o8:13 Curses of Dimensionality.
    o4:o1:13 Overview of Supervised Learning. [slides]
    o4:o1:13 Syllabus [pdf]

Final Project Presentations

    o6:o5:13 Mofei Li : Structured variable selection in support vector machines
    o6:o5:13 Xinkai Zhou : Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
    o6:o5:13 Juan Bernal : Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
    o6:o3:13 Jie Yang : Elastic SCAD as a novel penalization method for SVM classification tasks in high-dimensional data
    o6:o3:13 Li Pan : Variable selection for sparse Dirichlet-multinomial regression with an application to microbiome data analysis
    o6:o3:13 William Bohannon : Sparse least trimmed squares regression for analyzing high-dimensional large data sets
    o5:29:13 Fang Zheng : Central Limit Theorems and Multiplier Bootstrap when p is much larger than n

Final Project Reports

    o6:o5:13 Junjie Liu : Random walk loop soup
    o6:o5:13 Jiao Chen : Margin trees for high-dimensional classification
    o6:o5:13 Chao Zhang : Improved variable selection with Forward-Lasso adaptive shrinkage
    o6:o5:13 Tingyi Zhu : Multicategory Vertex Discriminant Analysis for High Dimensional Data
    o6:o5:13 Liang Weng : Sparsity considerations for dependent variables
    o6:o5:13 Xiaomin Xu : High Dimensional Sparse Econometric Models- An Introduction

Class Logistics

    Lecture: M&W 3:00-4:20pm, AP&M B412