IFT 6085 : Lectures

Books on structured prediction

Lecture 1 – 1/6 – introduction

Lecture 2 – 1/11 – structured prediction basics

Lecture 3 – 1/13 – structured prediction surrogate losses

Lecture 4 – 1/18 – convex optimization

Lecture 5 – 1/20 – convex optimization (bis)

Lecture 6 – 1/25 – structured SVM optimization (I)

Lecture 7 – 1/27 – structured SVM optimization (II)

Lecture 8 – 2/1 – structured SVM optimization (III)

Lecture 9 – 2/3 – structured SVM optimization (IV)

Lecture 10 – 2/8 – Frank-Wolfe algorithm

Lecture 11 – 2/10 – FW convergence

Lecture 12 – 2/15 – FW for SVMstruct

Lecture 13 – 2/17 – Polytopes

Lecture 14 – 2/22 – BCFW

Lecture 15 – 3/8 – Theory (binary classification)

Lecture 16 – 3/10 – Theory (structured prediction) - PAC-Bayes

Lecture 17 – 3/17 – Theory: generalization error bounds

Lecture 18 – 3/22 – Theory: consistency

Lecture 19 – 3/24 – CRF and variance reduced SGD

Lecture 20 – 3/29 – Variance reduced SGD (II)

Lecture 21 – 3/31 – Optimization (III)

Lecture 22 – 4/5 – latent variable; RNN

Lecture 23 – 4/7 – L2S & submodular optimization

Poster session – 4/28


Last modified: 2017-04-09