Syllabus for Machine Learning with Large Datasets 10-605 in Fall 2016

This is the syllabus for Machine Learning with Large Datasets 10-605 in Fall 2016.

---

Notes:

• Homeworks, unless otherwise posted, will be due when the next HW comes out.
• Lecture notes and/or slides will be (re)posted around the time of the lectures.
• Classes will be held on Oct 4
• No classes will be held on Nov 24 (Thanksgiving)

---

Schedule for 805 projects:

• 11:59pm Sun 10/2: Initial 805 project proposal due.
• 11:59pm Sun 10/16: Final 805 project proposal due.
  • This is a revised writeup that will address any comments William raises from the initial proposal.
• 11:59pm Sun 11/13: Midterm 805 project report due.
• 11:59pm Sun 12/11: Final 805 project writeup due.

If class time permits there will also be a short presentation in late Nov early Dec.

---

Schedule for lectures and 605 assignments:

• Tues Aug 30, 2016 Overview. Grading policies and etc, History of Big Data, Complexity theory and cost of important operations
• Thurs Sep 1, 2016 Probability Review. Counting for big data and density estimation, streaming Naive Bayes, Rocchio and TFIDF
  • Start work on Assignment 1a: Streaming NB. Writeup.
• Tues Sep 6, 2016 Streaming Naive Bayes. Notes on scalable naive bayes, Local counting in stream and sort
• Thurs Sep 8, 2016 Hadoop Overview. Intro to Hadoop, Hadoop Streaming
  • Start work on Assignment 1b: Streaming NB on Hadoop. Draft at https://autolab.andrew.cmu.edu/courses/10605-f16/assessments/hw1bhadoopnaivebayes/writeup
• Tues Sep 13, 2016 Workflows For Hadoop 1. Scalable classification, Scalable Rocchio and TFIDF, Abstracts for map-reduce algorithms, Joins in Hadoop, TFIDF in Pig, Guinea Pig intro, TFIDF in Guinea Pig
• Thurs Sep 15, 2016 Workflows For Hadoop 2. Similarity joins, Similarity joins with TFIDF, Parallel simjoins
  • Start work on Assignment 2: Naive bayes testing in Guinea Pig, draft at https://autolab.andrew.cmu.edu/courses/10605-f16/assessments/hw2nbwithguineapig/writeup
• Tues Sep 20, 2016 Workflows For Hadoop 3. PageRank in Pig, K-means in Pig, Spark, Systems built on top of Hadoop
• Thurs Sep 22, 2016 Phrase Finding. Phrase-finding in Pig, Other work with phrases
• Tues Sep 27, 2016 SGD and Hash Kernels. Learning as optimization, Logistic regression with SGD, Regularized SGD, Hash kernels for logistic regression
• Thurs Sep 29, 2016 Parallel Perceptrons 1. Also wrapup for SGD, debugging ML algorithms
  • Start work on Assignment 3: scalable SGD Draft at http://curtis.ml.cmu.edu/w/courses/images/8/86/Sgd_fall15.pdf
• Tues Oct 4, 2016 Parallel Perceptrons 2.
  • Start work on Assignment 3: scalable SGD Draft at http://curtis.ml.cmu.edu/w/courses/images/8/86/Sgd_fall15.pdf
• Thurs Oct 6, 2016 Parallel Perceptrons 3. Structured perceptrons, Interative parameter mixing paper
• Tues Oct 11, 2016 SGD for MF. Matrix factorization, Matrix factorization with SGD, distributed matrix factorization with SGD
• Thurs Oct 13, 2016 Midterm review.
  • Last assignment due
• Tues Oct 18, 2016 Midterm.
• Thurs Oct 20, 2016 Subsampling a Graph. Sampling a graph, Local partitioning
  • Start work on Assignment 4: Subsampling a Graph with Approximate PageRank, draft at https://drive.google.com/file/d/0BzQQ-spWKjhUaWoyOFZHV21uUlU/view
• Tues Oct 25, 2016 Deep Learning 1. Deep learning intro, Deep learning and GPUs, Expressiveness of MLPs, Exploding and vanishing gradients, Modern deep learning models
• Thurs Oct 27, 2016 Deep Learning 2. Reverse-mode differentiation, Recursive ANNs, Word2vec
• Tues Nov 1, 2016 Randomized Algorithms 1. Bloom filters, The countmin sketch
  • Start work on Assignment 5: Autodiff with IPM. This is a new assignment for Fall 2016.
• Thurs Nov 3, 2016 Randomized Algorithms 2. Locality sensitive hashing
• Tues Nov 8, 2016 Graph Architectures for ML. Graph-based ML architectures, Pregel, Signal-collect, GraphLab, PowerGraph, GraphChi, GraphX
• Thurs Nov 10, 2016 SSL on Graphs. Semi-supervised learning intro, Multirank-walk SSL method, Harmonic fields, Modified Adsorption SSL method, MAD with countmin sketches
• Tues Nov 15, 2016 Unsupervised Learning On Graphs. Spectral clustering, Power iteration clustering, Label propagation for clustering non-graph data, Label propagation for SSL on non-graph data
  • Start work on Assignment 6: To be decided, possibly using Spark/GraphX to do PIC or MRW.
• Thurs Nov 17, 2016 Parameter Servers.
• Tues Nov 22, 2016 LDA 1. DGMs for naive Bayes, Gibbs sampling for LDA
  • Start work on Assignment 7: LDA with a Parameter Server, draft http://curtis.ml.cmu.edu/w/courses/images/1/16/Hw7-lda-ps.pdf
• Tues Nov 29, 2016 LDA 2. Parallelizing LDA, Fast sampling for LDA, DGMs for graphs
• Thurs Dec 1, 2016 Scalable Probabilistic Logics.
• Tues Dec 6, 2016 Review session for final.
  • Last assignment due
• Thurs Dec 8, 2016 Final Exam.