IFT 6132 : Lectures - Winter 2023

Books on structured prediction

Part I: theory of structured prediction

Lecture 1 – 1/10 – introduction

Lecture 2 – 1/12 – structured prediction elements and examples

(No lectures on 1/17 and 1/19)

Lecture 3 – 1/24 – Energy-based models

Lecture 4 – 1/26 – Theory (binary classification)

Lecture 5 – 1/31 – Theory (structured prediction) - PAC-Bayes

Lecture 6 – 2/2 – Theory: generalization error bounds

Lecture 7 – 2/7 – Kernels and RKHS

Lecture 8 – 2/9 – Theory: calibrated convex surrogate losses

Part II: convex optimization and structured prediction

Lecture 9 – 2/14 – convex optimization

Lecture 10 – 2/16 – stochastic subgradient method

Lecture 11 – 2/21 – convex optimization (II) + structured SVM optimization (I)

Lecture 12 – 2/23 – structured SVM optimization (II) - small QP

Week of 2/27 - spring break (no lecture on 2/28 and 3/2)

Lecture 13 – 3/7 – structured SVM optimization (III) - M3-net

Lecture 14 – 3/9 – structured SVM optimization (IV) - duality

Lecture 15 – 3/14 – structured SVM optimization (V) - M3-net dual & cutting plane

Lecture 16 – 3/16 – FW & AFW algorithms

Lecture 17 – 3/21 – FW convergence

Lecture 18 - 3/23 – FW for SVMstruct

Lecture 19 - 3/28 – SAG method

Lecture 20 - 3/30 – CRF and variance reduced SGD

Lecture 21 – 4/4 – catalyst

lecture 22 – 4/6 – latent variable; RNN

lecture 23 – 4/11 – learning to search; SeaRNN; SPENs

Poster session – 4/27