9 520 6 860 statistical learning theory and applications
play

9.520/6.860: Statistical Learning Theory and Applications Class: - PowerPoint PPT Presentation

Mar 05, 2023 •790 likes •847 views

9.520/6.860: Statistical Learning Theory and Applications Class: Mon., Wed. 1:00 - 2:30 pm, 46-3310 (PILM Seminar Room) Office Hours: Friday 1:00 pm - 2:00 pm, 46-5156 (Poggio lab lounge) and/or 46-5165 (MIBR Reading Room) Web:

  1. 9.520/6.860: Statistical Learning Theory and Applications Class: Mon., Wed. 1:00 - 2:30 pm, 46-3310 (PILM Seminar Room) Office Hours: Friday 1:00 pm - 2:00 pm, 46-5156 (Poggio lab lounge) and/or 46-5165 (MIBR Reading Room) Web: http://www.mit.edu/~9.520/ Contact: 9.520@mit.edu Mailing list: 9.520students@mit.edu ● 9.520/6.860 will use Stellar ● Mailing list and web (announcements) for updates

  2. Material Slides — will be posted (for most lectures) Videos — check CBMM Notes — L. Rosasco and T. Poggio, Machine Learning: a Regularization Approach, MIT-9.520 Lectures Notes , Manuscript, Dec. 2016 (will be provided) For feedback on book (typos, errors, ...) https://goo.gl/forms/pQcewnsAV3lCNoyr1

  3. Grading policies ● Problem sets (0.6) ○ 6 problem sets (0.10 each) ○ See next slide for more details ● Project (0.3) ○ See later ● Participation (0.1) ○ Attending class lectures is required! ○ Sign-in sheet will be circulated 5 (random) times

  4. Problem sets ● Problem sets (0.6) ○ 6 problem sets (0.10 each) ■ 2 - 3 questions (demonstrations/exercises + short MATLAB) ■ 7 days due! ○ typeset in LaTeX (template provided) ○ online submission by due date; printed submission in next class ● Late policy ○ All students have 4 free late days (to be used on psets and project proposal) ○ You may use up to 2 late days per assignment with no penalty ○ Beyond this, we will deduct a late penalty of 50% of the grade per additional late day Dates (due times are 11:59 pm). Submission online (dbox link). [pset 1] Wed. Sep. 19, due: Tue., Sep. 25 [pset 2] Wed. Oct. 3, due: Tue., Oct. 09 [pset 3] Wed. Oct. 17, due: Tue., Oct. 23 [pset 4] Wed. Oct. 31, due: Tue., Nov. 06 [pset 5] Wed. Nov. 19, due: Tue., Nov. 25 [pset 6] Wed. Dec. 5, due: Tue., Dec. 11 Collaboration policy: You may discuss with others but need to work out your own solution.

  5. Projects A) Theory B) Algorithms C) Application ○ This is not a data science course, so we will not consider data preparation as contributing to the grade. D) Coding E) Wikipedia ● report (NIPS format): 4 pages ( + Appendix), 6 pages max OR ● poster session (last week of classes) Dates ● Abstract and title: Oct. 31 ● Feedback and approval: Nov. 7 ● Poster and revised abstract submission: Dec. 10 ● Poster presentations: Dec. 12 ● Report submission: Dec. 12

Recommend

MIT 9.520/6.860, Fall 2019 Statistical Learning Theory and Applications Class 02: Statistical

MIT 9.520/6.860, Fall 2019 Statistical Learning Theory and Applications Class 02: Statistical

MIT 9.520/6.860, Fall 2019 Statistical Learning Theory and Applications Class 02: Statistical Learning Setting Lorenzo Rosasco Learning from examples rather than being explicitly programmed. theory. L.Rosasco, 9.520/6.860 Fall 2018

582 views • 32 slides
9.5 .520/6.860: : Statistical Learning Theory ry and Applications Class: Tue, Thu 11:00 -

9.5 .520/6.860: : Statistical Learning Theory ry and Applications Class: Tue, Thu 11:00 -

9.5 .520/6.860: : Statistical Learning Theory ry and Applications Class: Tue, Thu 11:00 - 12:30 pm , 46-3002 (Singleton) Office Hours: Friday 1:00 pm - 2:00 pm, 46-5156 (Poggio lab lounge) and/or 46-5165 (MIBR Reading Room) Web:

325 views • 15 slides
Statistical Learning Theory and Applications 9.520/6.860 in Fall 2017 Class Times:

Statistical Learning Theory and Applications 9.520/6.860 in Fall 2017 Class Times:

Statistical Learning Theory and Applications 9.520/6.860 in Fall 2017 Class Times: Monday and Wednesday 1pm-2:30pm in 46-3310 Units: 3-0-9 H,G Web site: http://www.mit.edu/~9.520/ Email Contact : 9.520@mit.edu 9.520: Statistical

1.53k views • 149 slides
MIT 9.520/6.860, Fall 2018 Statistical Learning Theory and Applications Class 06: Learning with

MIT 9.520/6.860, Fall 2018 Statistical Learning Theory and Applications Class 06: Learning with

MIT 9.520/6.860, Fall 2018 Statistical Learning Theory and Applications Class 06: Learning with Stochastic Gradients Sasha Rakhlin A. Rakhlin, 9.520/6.860 2018 Why Optimization? Much (but not all) of Machine Learning: write down objective

481 views • 24 slides
Statistical Learning Theory and Applications 9.520/6.860 in Fall 2018 Class Times:

Statistical Learning Theory and Applications 9.520/6.860 in Fall 2018 Class Times:

Statistical Learning Theory and Applications 9.520/6.860 in Fall 2018 Class Times: Tomaso Poggio Tuesday and Thursday 11am-12:30pm in 46-3002 Singleton Auditorium (TP), Lorenzo Rosasco Units: 3-0-9 H,G (LR), Sasha Rakhlin (SR) Web

1.41k views • 86 slides
Statistical Learning Theory and Applications 9.520/6.860 in Fall 2016 Class Times:

Statistical Learning Theory and Applications 9.520/6.860 in Fall 2016 Class Times:

Statistical Learning Theory and Applications 9.520/6.860 in Fall 2016 Class Times: Monday and Wednesday 1pm-2:30pm in 46-3310 Units: 3-0-9 H,G Web site: http://www.mit.edu/~9.520/ Email Contact : 9.520@mit.edu Instructors: Tomaso

1.35k views • 90 slides
MIT 9.520/6.860 Statistical Learning Theory and Applications Class 0: Mathcamp Lorenzo Rosasco

MIT 9.520/6.860 Statistical Learning Theory and Applications Class 0: Mathcamp Lorenzo Rosasco

MIT 9.520/6.860 Statistical Learning Theory and Applications Class 0: Mathcamp Lorenzo Rosasco Vector Spaces Hilbert Spaces Functionals and Operators (Matrices) Linear Operators Probability Theory R D We like R D because we can add

513 views • 34 slides
COMPLETE STATISTICAL THEORY OF LEARNING LEARNING USING STATISTICAL INVARIANTS Vladimir Vapnik

COMPLETE STATISTICAL THEORY OF LEARNING LEARNING USING STATISTICAL INVARIANTS Vladimir Vapnik

COMPLETE STATISTICAL THEORY OF LEARNING LEARNING USING STATISTICAL INVARIANTS Vladimir Vapnik 1 PART I VC THEORY OF GENERALIZATION 2 THE MAIN QUESTION OF LEARNING THEORY QUESTION: When in set of functions { f ( x ) } we can minimize

1.18k views • 59 slides
MIT 9.520/6.860, Fall 2018 Statistical Learning Theory and Applications Class 04: Features and

MIT 9.520/6.860, Fall 2018 Statistical Learning Theory and Applications Class 04: Features and

MIT 9.520/6.860, Fall 2018 Statistical Learning Theory and Applications Class 04: Features and Kernels Lorenzo Rosasco Linear functions Let H lin be the space of linear functions f ( x ) = w x . f w is one to one, H := w

462 views • 35 slides
A Geometric Approach to Statistical Learning Theory Shahar Mendelson Centre for Mathematics and

A Geometric Approach to Statistical Learning Theory Shahar Mendelson Centre for Mathematics and

A Geometric Approach to Statistical Learning Theory Shahar Mendelson Centre for Mathematics and its Applications The Australian National University Canberra, Australia What is a learning problem A class of functions F on a probability

562 views • 32 slides
Statistical Learning Theory Real-World Process and PAC-Learning Training Set New

Statistical Learning Theory Real-World Process and PAC-Learning Training Set New

Learning Classifiers Statistical Learning Theory Real-World Process and PAC-Learning Training Set New Examples CS678 Advanced Topics in Machine Learning Thorsten Joachims Classifier Learner Spring

96 views • 5 slides
MIT 9.520/6.860, Fall 2017 Statistical Learning Theory and Applications Class 20: Dictionary

MIT 9.520/6.860, Fall 2017 Statistical Learning Theory and Applications Class 20: Dictionary

MIT 9.520/6.860, Fall 2017 Statistical Learning Theory and Applications Class 20: Dictionary Learning What is data representation? Let X be a data-space ( M ) M ( M ) F X X A data representation is a map : X F ,

804 views • 56 slides
Overview of statistical learning theory Daniel Hsu Columbia TRIPODS Bootcamp 1 Statistical

Overview of statistical learning theory Daniel Hsu Columbia TRIPODS Bootcamp 1 Statistical

Overview of statistical learning theory Daniel Hsu Columbia TRIPODS Bootcamp 1 Statistical model for machine learning 2 Basic goal of machine learning Goal : Predict outcome y from set of possible outcomes Y , on the basis of observation x

362 views • 32 slides
The Theory of Quantum Statistical Comparison and Some Applications in Quantum Information

The Theory of Quantum Statistical Comparison and Some Applications in Quantum Information

The Theory of Quantum Statistical Comparison and Some Applications in Quantum Information Sciences Francesco Buscemi (Nagoya U) The 39th Quantum Information Technologies Symposium (QIT) . RCAST, The University of Tokyo, 27 November 2018 The

502 views • 33 slides
Statistical and Computational Statistical and Computational Learning Theory Learning Theory

Statistical and Computational Statistical and Computational Learning Theory Learning Theory

Statistical and Computational Statistical and Computational Learning Theory Learning Theory Fundamental Question: Predict Error Rates Fundamental Question: Predict Error Rates Given: Given: The space H of hypotheses The space H of

497 views • 29 slides
Learning to Reconstruct Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs,

Learning to Reconstruct Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs,

Learning to Reconstruct Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs, Marie-Sarah Lacharit, Brice Minaud, Kenny Paterson CASYS team seminar, Grenoble, December 2018 Outsourcing Data with Search Capabilities Data

534 views • 38 slides
Statistical Learning Theory Machine Learning Summer School, Kyoto, Japan Alexander (Sasha)

Statistical Learning Theory Machine Learning Summer School, Kyoto, Japan Alexander (Sasha)

Statistical Learning Theory Machine Learning Summer School, Kyoto, Japan Alexander (Sasha) Rakhlin University of Pennsylvania, The Wharton School Penn Research in Machine Learning (PRiML) August 27-28, 2012 1 / 130 References Parts of these

1.69k views • 149 slides
Learning to Reconstruct: Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs ,

Learning to Reconstruct: Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs ,

Learning to Reconstruct: Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs , Marie-Sarah Lacharit, Brice Minaud, Kenny Paterson pag225@cornell.edu, @pag_crypto Outsourced Databases Database Encrypting Outsourced

705 views • 23 slides
Computational and Statistical Learning Theory TTIC 31120 Prof. Nati Srebro Lecture 7:

Computational and Statistical Learning Theory TTIC 31120 Prof. Nati Srebro Lecture 7:

Computational and Statistical Learning Theory TTIC 31120 Prof. Nati Srebro Lecture 7: Computational Complexity of Learning Hardness of Improper Learning (continued) Agnostic Learning Hardness of Learning via Crypto Easy to generate

433 views • 24 slides
The Theory of Statistical Comparison with Applications in Quantum Information Science Francesco

The Theory of Statistical Comparison with Applications in Quantum Information Science Francesco

The Theory of Statistical Comparison with Applications in Quantum Information Science Francesco Buscemi (Nagoya University) buscemi@is.nagoya-u.ac.jp Tutorial Lecture for AQIS2016 Academia Sinica, Taipei, Taiwan 28 August 2016 these slides are

538 views • 26 slides
Learning to Reconstruct Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs,

Learning to Reconstruct Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs,

Learning to Reconstruct Statistical Learning Theory and Encrypted Database Attacks Paul Grubbs, Marie-Sarah Lacharit, Brice Minaud, Kenny Paterson eprint 2019/011 and IEEE S&P 2019. C2 seminar, Rennes, 2019 Outsourcing Data Data upload

646 views • 39 slides
Learning Theory: Some Principles and Applications Joshua A. Danish IU Learning Sciences How do

Learning Theory: Some Principles and Applications Joshua A. Danish IU Learning Sciences How do

Learning Theory: Some Principles and Applications Joshua A. Danish IU Learning Sciences How do people learn? Think-Pair-Share Jot down a few notes Discuss with a neighbor Share out How might this inform your teaching? Next

272 views • 11 slides
Statistical Learning Theory and Support Vector Machines Gert Cauwenberghs Johns Hopkins

Statistical Learning Theory and Support Vector Machines Gert Cauwenberghs Johns Hopkins

Statistical Learning Theory and Support Vector Machines Gert Cauwenberghs Johns Hopkins University gert@jhu.edu 520.776 Learning on Silicon http://bach.ece.jhu.edu/gert/courses/776 G. Cauwenberghs 520.776 Learning on Silicon Statistical

758 views • 38 slides
Ultra-high dimensional statistics and statistical learning on some applications Dominique Picard

Ultra-high dimensional statistics and statistical learning on some applications Dominique Picard

Examples Linear model Mathematical ingredients LOL algo Ultra-high dimensional statistics and statistical learning on some applications Dominique Picard Universit e Paris-Diderot Laboratoire Probabilit es et Mod` eles Al eatoires

1.19k views • 86 slides

More recommend