10418 + 10618, Fall 2022
School of Computer Science
Carnegie Mellon University
This schedule is tentative and subject to change. Please check back often.
Date  Lecture  Readings  Announcements 

Searchbased Structured Prediction 

Mon, 29Aug  Lecture 1
:
Course Overview / What is Structured Prediction? [Slides] [Slides (Inked)] [Whiteboard (OneNote)] 


Wed, 31Aug  Lecture 2
:
Recurrent neural networks (RNNs) / Modulebased Automatic Differentiation [Slides] [Slides (Inked)] [Whiteboard (OneNote)] 


Fri, 2Sep 
(No Recitation) 


Mon, 5Sep 
(No Class: Labor Day) 


Wed, 7Sep  Lecture 3
:
1D CNNs / Sequencetosequence Models [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 

HW1 out

Fri, 9Sep 
Recitation: HW1 [Handout] [Whiteboard (OneNote)] 


Mon, 12Sep  Lecture 4
:
Learning to Search (Part I): MLE & Decoding for seq2seq / Imitation Learning [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 


Wed, 14Sep  Lecture 5
:
Learning to Search (Part II): Imitation Learning / Structured Prediction as Search [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 


Fri, 16Sep 
(No Recitation) 

HW1 due

Sat, 17Sep  Lecture 5.5
:
Learning to Search (Part III): Imitation Learning for Structured Prediction [video recorded] [Slides] [Slides (Inked)] [Whiteboard (PDF)] 

HW2 out

Graphical Models: Representation, Exact Inference, and Learning 

Mon, 19Sep  Lecture 6
:
Directed Graphical Models / Undirected Graphical Models [Slides] [Whiteboard (OneNote)] [Poll] 


Wed, 21Sep 
Recitation: HW2 [Handout] [Whiteboard (OneNote)] 

HW1 Solution Session 
Fri, 23Sep  Lecture 7
:
DGM & UGM Conditional Independencies / Factor Graphs [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 


Mon, 26Sep  Lecture 8
:
Exact Marginal/MAP Inference: Variable Elimination & Belief Propagation [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 


Wed, 28Sep  Lecture 9
:
Belief Propagation / Learning fully observable MRFs [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 


Thu, 29Sep 


HW2 due HW3 out

Fri, 30Sep 
(No Recitation) [Whiteboard (OneNote)] 


Mon, 3Oct  Lecture 10
:
Learning fully observable CRFs / Neural Potential Functions / MBR Decoding [Slides] [Slides (Inked)] [Whiteboard (OneNote)] [Poll] 

HW2 Solution Session 
Tue, 4Oct 
Recitation: HW3 (evening) [Handout] [Solutions] 


Approximate Inference: MCMC 

Wed, 5Oct  Lecture 11
:
Complexity of Inference / Monte Carlo Methods [Slides] [Slides (Inked)] [Whiteboard (OneNote)] [Poll] 


Fri, 7Oct 
(No Recitation) 


Mon, 10Oct  Lecture 12
:
Midterm Exam Review / Markov Chain Monte Carlo: Gibbs Sampling & MetropolisHastings [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 

HW3 due (only two grace/late days permitted) Practice Exam out

Wed, 12Oct  Lecture 13
:
Markov Chains / Bayesian Inference for Parameter Estimation [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Whiteboard (OneNote)] [Poll] 


Fri, 14Oct 
Midterm Exam 


Mon, 17Oct 
Fall break 


Tue, 18Oct 



Wed, 19Oct 
Fall break 


Thu, 20Oct 



Fri, 21Oct 
Fall break 


Mon, 24Oct  Lecture 14
:
Bayesian Inference for Parameter Estimation / Topic Modeling [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 

HW4 out

Mon, 24Oct 
Recitation: HW4 (evening recitation, 6pm, GHC 6121) [Handout] [Solutions] 


Wed, 26Oct  Lecture 15
:
Topic Modeling / Convolutional Neural Networks [Slides] [Slides (Inked)] [Poll] 


Fri, 28Oct 
Tartan Community Day 


Approximate Inference: Variational Methods 

Mon, 31Oct  Lecture 16
:
Mean Field Variational Inference [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 


Wed, 2Nov  Lecture 17
:
Coordinate Ascent Variational Inference [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 


Fri, 4Nov  Lecture 18
:
CAVI / Expectation Maximization [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 

HW4 due HW5 out

Mon, 7Nov 
Recitation: HW5 [Handout] 


Wed, 9Nov  Lecture 19
:
Variational EM / Hidden State CRFs [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 


Fri, 11Nov 
(No recitation) 


Mon, 14Nov  Lecture 20
:
Variational Autoencoders [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 


Advanced Topics 

Wed, 16Nov  Lecture 21
:
MAP Inference: Mixed Integer Linear Programming [Slides] [Whiteboard (PDF)] [Poll] 

HW5 due HW6 out

Fri, 18Nov 
Recitation: HW6 [Handout] 


Mon, 21Nov  Lecture 22
:
Structured Perceptron / Structured SVM [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 


Wed, 23Nov 
Thanksgiving Holiday No class 


Thu, 24Nov 
Thanksgiving Holiday No class 


Fri, 25Nov 
Thanksgiving Holiday No class 


Mon, 28Nov  Lecture 23
:
Causal Inference [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 

MiniProject out

Wed, 30Nov  Lecture 24
:
Causal Inference / Bayesian Nonparametrics [Slides] [Slides (Inked)] [Poll] 

HW6 due

Fri, 2Dec 
(No recitation) 


Mon, 5Dec 
(Lecture rescheduled to Friday) 

Practice Exam out

Wed, 7Dec  Lecture 25
:
Bayesian Nonparametrics / Graph Neural Networks [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 


Fri, 9Dec  Lecture 26
:
Graph Neural Networks / Final Exam Review [Slides] [Slides (Inked)] [Whiteboard (PDF)] [Poll] 

MiniProject due

Thu, 15Dec 
Final Exam (5:30 pm  7:30 pm, DH A302) 

