Difference between revisions of "Syllabus for Machine Learning with Large Datasets 10-605 in Spring 2015"

From Cohen Courses
Jump to navigationJump to search
 
(132 intermediate revisions by 5 users not shown)
Line 2: Line 2:
  
 
Notes:  
 
Notes:  
−
* The assignments are from 2014, and will be modified over the course of the semester - some may be changed substantially.
+
* The assignments posted are '''drafts''' based on the assignments from 2014, and will be modified over the course of the semester - some may be changed substantially.
−
* Lecture notes and/or slides will be posted around the time of the lectures.
+
* Lecture notes and/or slides will be (re)posted around the time of the lectures.
  
 
== January ==
 
== January ==
Line 9: Line 9:
 
* Tues Jan 13. [[Class meeting for 10-605 Overview|Overview of course, cost of various operations, asymptotic analysis.]]
 
* Tues Jan 13. [[Class meeting for 10-605 Overview|Overview of course, cost of various operations, asymptotic analysis.]]
 
* Thus Jan 15. [[Class meeting for 10-605 Probability Review|Review of probabilities, joint distributions and naive Bayes]]
 
* Thus Jan 15. [[Class meeting for 10-605 Probability Review|Review of probabilities, joint distributions and naive Bayes]]
 +
** ''HW1A: streaming Naive Bayes 1 (with feature counts in memory)''. [http://www.cs.cmu.edu/~yipeiw/TA605/hw1A/hashtable-nb_s15.pdf PDF Handout]
 
* Tues Jan 20.  [[Class meeting for 10-605 Streaming Naive Bayes|Streaming algorithms and Naive Bayes; The stream-and-sort design pattern; Naive Bayes for large feature sets.]]
 
* Tues Jan 20.  [[Class meeting for 10-605 Streaming Naive Bayes|Streaming algorithms and Naive Bayes; The stream-and-sort design pattern; Naive Bayes for large feature sets.]]
−
** ''New Assignment: streaming Naive Bayes 1 (with feature counts in memory)''. [http://curtis.ml.cmu.edu/w/courses/images/6/6d/Hashtable-nb.pdf PDF Handout]
+
** ''HW1B: streaming Naive Bayes 2 (with feature counts on disk) with stream-and-sort''. [http://www.cs.cmu.edu/afs/cs/user/rgoutam/www/Assignment_1b.pdf PDF Handout]
−
* Thus Jan 22. [[Class meeting for 10-605 Phase Finding|Messages and records 1; Phrase finding.]]
+
** For 10/11-805 students: '''a one-paragraph summary of a recent research result you'd like to present is due.'''  If you're planning/hoping to transfer from 605, but haven't yet transferred, then also submit this assignment.  Email to wcohen+805 AT gmail.com with the subject "Presentation" and include, in addition to your summary:
−
** '''Assignment due: streaming Naive Bayes 1 (with feature counts in memory)'''. 
+
***Your name and andrew id
−
* Tues Jan 27. [[Class meeting for 10-605 Rocchio and On-line Learning|Phrase Finding and Rocchio]]
+
*** A link to the paper
−
** ''New Assignment: streaming Naive Bayes 2 (with feature counts on disk) with stream-and-sort''. [http://curtis.ml.cmu.edu/w/courses/images/0/0d/Stream-nb.pdf PDF Handout]
+
*** Your best guess as to what lectures should precede the presentation
−
* Thus Jan 29. [[Class meeting for 10-605 Parallel Perceptrons|Rocchio and Parallel Perceptrons]]
+
*** '''Due by 11:59:59pm EST Tuesday.'''
 +
* Thus Jan 22. [[Class meeting for 10-605 Phase Finding|Messages, records and workflows; Phrase finding.]]
 +
* Tues Jan 27. [[Class meeting for 10-605 Hadoop 1|Hadoop and Map-Reduce]]
 +
* Thus Jan 29. [[Class meeting for 10-605 PIG|PIG and Other Workflow Systems for Hadoop]]
 +
** '''HW1A and HW1B due.'''
 +
** ''HW2: phrase finding with stream-and-sort''. [http://www.cs.cmu.edu/~yipeiw/TA605/phrases.pdf PDF Handout] [http://www.cs.cmu.edu/~yipeiw/TA605/stopword.list Stopword List]
  
 
== February ==
 
== February ==
  
−
* Tues Feb 3. [[Class meeting for 10-605 Hadoop 1|Perceptrons/Map-reduce and Hadoop]].
+
* Tues Feb 3. [[Class_meeting_for_10-605_Rocchio_and_On-line_Learning|Rocchio and TFIDF]]
−
** '''Assignment due: streaming Naive Bayes 2 (with feature counts on disk) with stream-and-sort'''
+
* Thus Feb 5.  [[Class meeting for 10-605 Similarity Joins|Fast KNN and similarity joins]]
−
** ''New Assignment: phrase finding with stream-and-sort''. [http://curtis.ml.cmu.edu/w/courses/images/5/5e/Phrases.pdf PDF Handout]
+
* Tues Feb 10. [[Class meeting for 10-605 Parallel Perceptrons 1|Parallel Perceptrons 1]].
−
* Thus Feb 5. [[Class meeting for 10-605 Parallel Perceptrons 2|Parallel Perceptrons]].
+
* Thus Feb 12. [[Class meeting for 10-605 Parallel Perceptrons 2|Parallel Perceptrons 2]].
 +
** '''HW2 due: phrase finding with stream-and-sort'''
 +
* Tues Feb 17. [[Class meeting for 10-605 SGD and Hash Kernels|Scalable SGD and Hash Kernels]]
 +
** ''HW3: Naive Bayes with Hadoop MapReduce''. PDF Handouts: [http://www.andrew.cmu.edu/user/amaurya/docs/10605/homework3.pdf HW3].
 +
** ''For 10/11-805 students:'' '''initial draft of project proposal is due.'''  I will give you feedback on this, so please be clear about your proposal.  I'm expecting approximately one page.  You should discuss what dataset you plan to use, what results you hope to obtain, what baseline technique you will build on and/or compare to.  Also include a section saying if you have a partner; and if you are willing to work with/mentor one or more 605 students, and if so, how you anticipate them contributing to the project.
 +
* Thus Feb 19. [[Class meeting for 10-605 Randomized|Randomized Algorithms 1]]
 +
* Tues Feb 24. [[Class meeting for 10-605 Randomized|Randomized Algorithms 2]]
 +
* Thus Feb 26. [[Class meeting for 10-605 SGD for MF|Matrix Factorization and SGD]]
  
−
'''stopped changes'''
+
== March  ==
  
−
* Mon Feb 17. [[Class meeting for 10-605 SGD and Hash Kernels|Scalable SGD and Hash Kernels]]
+
* Sun Mar 1.
−
** '''Assignment due: phrase finding with stream-and-sort'''
+
** '''HW3 due: Naive Bayes with Hadoop MapReduce'''
−
** ''New Assignments: Naive Bayes with Streaming Hadoop, Naive Bayes with Hadoop & Phrase-finding with Hadoop''. [http://curtis.ml.cmu.edu/w/courses/images/c/c0/Homework4a.pdf PDF Handout (4a)][http://curtis.ml.cmu.edu/w/courses/images/a/a2/Homework4b.pdf PDF Handout (4b)][http://curtis.ml.cmu.edu/w/courses/images/3/30/Homework4c.pdf PDF Handout (4c)]
+
** HW4: [http://www.andrew.cmu.edu/user/amaurya/docs/10605/homework4.pdf PDF wrteup]
−
* Wed Feb 19. [[Class meeting for 10-605 SGD for MF|Matrix Factorization and SGD, plus another Hadoop demo]]
+
* Tues Mar 3. ''student presentations''
−
* Fri Feb 21. ''Nothing due - the streaming run for Naive Bayes, 4(a), has been postponed till Monday.''
+
** Adams Wei Yu (weiyu at andrew): fast PPR on Map-Reduce [http://www.cs.cmu.edu/~wcohen/10-605/2015-guest-lecture/ppr_mapreduce.pdf]
−
* Mon Feb 24. [[Class meeting for 10-605 SGD for MF 2 and Randomized Algorithms|SGD for Matrix Factorization, and Randomized Algorithms 1 (Bloom Filters)]]
+
** Jakub Pachocki: factorization machines (and hash kernels?) [http://www.cs.cmu.edu/~wcohen/10-605/2015-guest-lecture/FM.pdf]
−
** '''Streaming run on Hadoop of Naive Bayes due'''  
+
** <strike>Wanli Ma (wanlim at andrew): coresets for k-segmentation of streams</strike>
−
* Wed Feb 26. [[Class meeting for 10-605 Graphs 2|Randomized Algorithms]]
+
* Thus Mar 5. ''student presentations''
−
* Fri Feb 28.
+
** Quiz: [https://qna-app.appspot.com/view.html?aglzfnFuYS1hcHByGQsSDFF1ZXN0aW9uTGlzdBiAgIDAvI2ZCAw]
−
** '''Non-streaming run on Hadoop of Naive Bayes due.'''
+
** Matt Gardner (mg1 at cs): Large-scale extensions of the path ranking algorithm [http://www.cs.cmu.edu/~wcohen/10-605/2015-guest-lecture/matt-805-presentation.pdf]
 +
** Jesse Dodge (jessed at andrew): large-scale lasso regularization [http://www.cs.cmu.edu/~wcohen/10-605/2015-guest-lecture/jesse.pdf]
 +
** Ishan Misra (imisra at andrew): LSH for object detection [http://www.cs.cmu.edu/~wcohen/10-605/2015-guest-lecture/ishan.pdf]
 +
** ''HW5: memory-efficient SGD'' [http://www.andrew.cmu.edu/user/amaurya/docs/10605/homework5.pdf PDF handout]
 +
** ''For 10/11-805 students:'' '''project proposal is due.'''  This must contain a complete description of the data you will use.
 +
* Sat Mar 7 ('''extended from Friday'''):
 +
** '''HW4 due: Phrase-finding with Hadoop'''
 +
* Tues Mar 10. ''no class - spring break.''
 +
* Thus Mar 12. ''no class - spring break.''
 +
* Tues Mar 17. [[Class meeting for 10-605 Subsample A Graph|Scalable PageRank]] [http://curtis.ml.cmu.edu/w/courses/images/e/eb/ApproxPageRank.pdf PDF handout]
 +
* Thus Mar 19. [[Class meeting for 10-605 Subsampling Graphs|Subsampling a graph with RWR]]
 +
** '''HW5 due: memory-efficient SGD'''
 +
** ''HW6: Subsampling and visualizing a graph.  [http://bit.ly/605_hw6 PDF handout]
 +
* Tues Mar 24.  
 +
** Student presentation: Rohan Ramanath, Bayesian Optimization
 +
** Guest lecture: Dai Wei, CMU, Parameter servers.  ('''Note''': This will be very relevant for one of the later HWs) [https://dl.dropboxusercontent.com/u/65353654/daiwei01_release.pdf PDF] and [https://dl.dropboxusercontent.com/u/65353654/daiwei01_release.pptx ppt].
 +
* Thus Mar 26. Guest lecture: D. Sculley, Google, TBA
 +
* Tues Mar 31. [[Class meeting for 10-605 LDA 1|Sparse sampling and parallelization for LDA]]
  
−
== March ==
+
== April and May ==
 +
 
 +
* Wed April 1
 +
** '''HW6 due: Subsampling and visualizing a graph.'''
 +
** ''HW7: Matrix Factorization in Spark'' [http://www.andrew.cmu.edu/user/amaurya/docs/10605/homework7.pdf HW7 PDF Handout] [http://www.cs.cmu.edu/~yipeiw/TA605/hw7/eval2.pyc Evaluation Script][http://www.cs.cmu.edu/~yipeiw/TA605/hw7/eval_acc.py Validation Script]
 +
* Thus Apr 2. [[Class meeting for 10-605 2013 LDA 2|Speeding up LDA-like models: All-reduce and other tricks]]
 +
* Tues Apr 7. Guest lecture - Alex Beutel, SGD for Tensors
 +
** [http://www.cs.cmu.edu/~wcohen/10-605/2015-guest-lecture/beutel.pptx Alex's slides]
 +
** William's [http://www.cs.cmu.edu/~wcohen/10-605/HintsForMF.pptx hints for HW7 in PPT],[http://www.cs.cmu.edu/~wcohen/10-605/HintsForMF.pdf Hints for HW7 in PDF]
 +
* Thus Apr 9. Guest lecture - Alex Smola, [http://www.cs.cmu.edu/~wcohen/10-605/2015-guest-lecture/smola-param-serve.pdf Scalable parameter servers]
 +
** If you don't like the MediaTech one, a [http://youtu.be/bFnUeYDBtbk Youtube video on is also available] for Alex's talk.
 +
* Mon Apr 13. '''Informal update due for students working on project teams due.'''
 +
** Each '''student working on a project''' should send to wcohen+805@gmail.com an update, between 1/2 page and 1 page long, saying what concrete tasks you've accomplished to date, how these tasks are part of the overall project (if you're not the only member), and what you plan to do between 4/13 and the presentation on 4/23. 
 +
** Additionally, each '''project lead''' (i.e., each 805 student that has any 10-605 student working with them) should add a list of who's working on their project, and one line indicating if they're making good progress so far.
 +
* Tues Apr 14.  [[Class_meeting_for_10-605_SSL_on_Graphs|SSL on Graphs]]
 +
* Thus Apr 16. ''no class : carnival''
 +
** '''HW7 due'''
 +
** ''HW8: [http://bit.ly/605_hw8_ps Matrix factorization on parameter server]
 +
* Tues Apr 21.  [[Class meeting for 10-605 GraphLab|Graph models for large-scale ML]]
 +
* Thus Apr 23.  ''Presentation for 10/11-805 projects''
 +
* Tues Apr 28. Exam review session.
 +
** '''HW8: due'''
 +
** [http://www.cs.cmu.edu/~wcohen/10-605/practice-questions/s2014-final.pdf PDF practice questions from 2014]
 +
** [http://www.cs.cmu.edu/~wcohen/10-605/practice-questions/s2015-final.pdf PDF practice questions for 2015]
 +
** [http://www.cs.cmu.edu/~wcohen/10-605/exam-review.pptx Review session slides],  [http://www.cs.cmu.edu/~wcohen/10-605/exam-review.pdf PDF]
 +
* Thus Apr 30. In-class exam.
  
−
* Mon Mar 3. ''Guest Lecture: Garth Gibson, Cloud Computing and Programming Paradigms''
+
* Tues May 5.
−
** Slides: [http://www.cs.cmu.edu/~wcohen/10-605/garth-Intro.pptx Intro], [http://www.cs.cmu.edu/~wcohen/10-605/garth-MapReduce_majd.pdf Mapreduce], [http://www.cs.cmu.edu/~wcohen/10-605/garth-Programming.pptx Programming], [http://www.cs.cmu.edu/~wcohen/10-605/garth-UseCases.pptx Use Cases]
+
** ''For 10/11-805 students:'' '''project reports''' are due
−
* Wed Mar 5. ''Guest lecture: Alex Beutel, SGD on Hadoop''
 
−
** [http://www.cs.cmu.edu/~wcohen/10-605/alex-beutel.pptx Slides]
 
−
* Fri Mar 7.
 
−
** '''Hadoop assignment (phrase-finding) due'''
 
−
* Mon Mar 10. ''no class - spring break.''
 
−
* Wed Mar 12. ''no class - spring break.''
 
−
* Mon Mar 17. [[Class meeting for 10-605 Subsample A Graph|Scalable PageRank]]
 
−
** ''New Assignment: memory-efficient SGD'' [http://curtis.ml.cmu.edu/w/courses/images/0/08/Sgd.pdf PDF handout]
 
−
* Wed Mar 19. [[Class meeting for 10-605 Subsampling Graphs|Subsampling a graph with RWR]]
 
−
* Mon Mar 24. [[Class meeting for 10-605 SSL on Graphs|Subsamping continued and SSL on Graphs]]
 
−
* Wed Mar 26. [[Class meeting for 10-605 Spectral Clustering|Scalable spectral clustering techniques.]]
 
−
** <strike>Assignment due: memory-efficient SGD</strike> delayed to Mon 3/31
 
−
* Mon Mar 31. [[Class meeting for 10-605 LDA 1|Sparse sampling and parallelization for LDA]]
 
−
** '''Assignment due: memory-efficient SGD'''
 
−
** ''New Assignment: Subsampling and visualizing a graph.'' [http://curtis.ml.cmu.edu/w/courses/images/e/eb/ApproxPageRank.pdf PDF handout]
 
  
−
== April and May ==
+
== Topics covered in previous years but not in 2015 ==
  
−
* Wed Apr 2. [[Class meeting for 10-605 2013 LDA 2|Speeding up LDA-like models: All-reduce and online LDA]]
+
* [[Class meeting for 10-605 PIG|Workflows in PIG]]
−
* Mon Apr 7. [[Class meeting for 10-605 PIG|Workflows in PIG]]
+
* [[Class meeting for 10-605 First-Order Logics|First-order logics]]
−
* Wed Apr 9. [[Class meeting for 10-605 Similarity Joins|Fast KNN and similarity joins]]
+
* [[Class meeting for 10-605 Scalable FOL|Scalable First-order logics]]
−
* Mon Apr 14.  [[Class meeting for 10-605 Parallel Similarity Joins|Parallel/Scalable Similarity Joins]]
+
* [[Class meeting for 10-605 Parallel Similarity Joins|Scalable Similarity Joins]]
−
** '''Assignment due: Subsampling and visualizing a graph.'''
+
* [[Class meeting for 10-605 Rocchio and On-line Learning|Messages, records and workflows; Rocchio]]
−
** ''New Assignment: Workflows with Pig'' [http://curtis.ml.cmu.edu/w/courses/images/4/46/Nb_pig.pdf PDF handout]
+
* [[Class meeting for 10-605 Spectral Clustering|Scalable spectral clustering techniques.]]
−
* Wed Apr 16.  [[Class meeting for 10-605 First-Order Logics|First-order logics]]
+
* [http://www.cs.cmu.edu/~wcohen/10-605/schimmy.pptx Scalable pagerank - The Schimmy Pattern]
−
* Mon Apr 21. [[Class meeting for 10-605 Scalable FOL|Scalable First-order logics]]
 
−
* Wed Apr 23.   [[Class meeting for 10-605 GraphLab|Graph models for large-scale ML]]
 
−
** '''Assignment due: Workflows with Pig'''
 
−
* Mon Apr 28. Exam review session.
 
−
** [http://curtis.ml.cmu.edu/w/courses/images/0/0a/Practice_questions.pdf PDF practice questions]
 
−
** [http://www.cs.cmu.edu/~wcohen/10-605/exam-review.pptx Review session slides]
 
−
* Wed Apr 30. In-class exam.
 

Latest revision as of 14:50, 14 October 2015

This is the syllabus for Machine Learning with Large Datasets 10-605 in Spring 2015.

Notes:

  • The assignments posted are drafts based on the assignments from 2014, and will be modified over the course of the semester - some may be changed substantially.
  • Lecture notes and/or slides will be (re)posted around the time of the lectures.

January

February

March

  • Sun Mar 1.
    • HW3 due: Naive Bayes with Hadoop MapReduce
    • HW4: PDF wrteup
  • Tues Mar 3. student presentations
    • Adams Wei Yu (weiyu at andrew): fast PPR on Map-Reduce [1]
    • Jakub Pachocki: factorization machines (and hash kernels?) [2]
    • Wanli Ma (wanlim at andrew): coresets for k-segmentation of streams
  • Thus Mar 5. student presentations
    • Quiz: [3]
    • Matt Gardner (mg1 at cs): Large-scale extensions of the path ranking algorithm [4]
    • Jesse Dodge (jessed at andrew): large-scale lasso regularization [5]
    • Ishan Misra (imisra at andrew): LSH for object detection [6]
    • HW5: memory-efficient SGD PDF handout
    • For 10/11-805 students: project proposal is due. This must contain a complete description of the data you will use.
  • Sat Mar 7 (extended from Friday):
    • HW4 due: Phrase-finding with Hadoop
  • Tues Mar 10. no class - spring break.
  • Thus Mar 12. no class - spring break.
  • Tues Mar 17. Scalable PageRank PDF handout
  • Thus Mar 19. Subsampling a graph with RWR
    • HW5 due: memory-efficient SGD
    • HW6: Subsampling and visualizing a graph. PDF handout
  • Tues Mar 24.
    • Student presentation: Rohan Ramanath, Bayesian Optimization
    • Guest lecture: Dai Wei, CMU, Parameter servers. (Note: This will be very relevant for one of the later HWs) PDF and ppt.
  • Thus Mar 26. Guest lecture: D. Sculley, Google, TBA
  • Tues Mar 31. Sparse sampling and parallelization for LDA

April and May

  • Tues May 5.
    • For 10/11-805 students: project reports are due

Topics covered in previous years but not in 2015

Retrieved from "http://curtis.ml.cmu.edu/w/courses/index.php?title=Syllabus_for_Machine_Learning_with_Large_Datasets_10-605_in_Spring_2015&oldid=17890"