Lecture 2: Weighted Majority Algorithm
|
|
- Clifford Crawford
- 5 years ago
- Views:
Transcription
1 EECS 598-6: Prediction, Learning and Games Fall 3 Lecture : Weighted Majority Algorithm Lecturer: Jacob Abernethy Scribe: Petter Nilsson Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal publications.. Course announcements A GSI will likely) be recruited to the course. For now, office hours are Tuesday pm-pm. Homework is about to be posted, due 9/3. Group work is encouraged for homework.. Predictive sorting revisited Lecture ended by studying the problem of predicting the outcomes of games played among k teams, where a game between two of these k teams is played in every round. Assume the outcomes y s, s =... t in t rounds have been observed for pairs of teams i, j ),..., i t, j t ). Further assume that there eists a perfect ranking π S k determining the outcomes y s of each game. Without loss of generality WLOG) assume π i s ) < π j s ) for s =,..., t. In round t, the pair i t, j t ) is observed. The Halving algorithm makes a prediction ŷ t of the outcome y t by comparing the number of members of the following sets: C < t := {π S k πi s ) < πj s ) s =,..., t and πi t ) < πj t )},.) C t > := {π S k πi s ) < πj s ) s =,..., t and πi t ) > πj t )}..) The prediction follows majority vote, i.e. { < if C < t C > t, ŷ t =.3) > otherwise. The naive way to determine ŷ t is to enumerate S k and eliminate permutations that are inconsistent with past outcomes. This is however not efficient since S k = k!. The problem of computing the quantitites C t < and C t > is in fact #P -hard. The outcomes can be recorded in a directed acyclic graph DAG), and the problem is equivalent to finding the number of topological orderings of that graph, which is known to be #P -complete []. Challenge Problem) Continuation from last lecture: Is the problem of determining the largest of these two sets also #P -complete, or is there an efficient algorithm?.3 Review of basics in Conve Analysis Definition. A function f : R n R is conve if and only if any of the following conditions hold: a) For all, y R n, f) + + y fy) f )..4) -
2 Lecture : Weighted Majority Algorithm - b) For all, y R n and α [, ], c) For all random variables X, Jensen s inequality is satisfied. α)f) + αfy) f α) + αy)..5) EfX) fex)).6) Remark. As seen in.6), Jensen s inequality can actually be used to define conveness. Eercise) Prove that.4)-.6) are equivalent. Proposition.3 A sufficient condition for f to be conve is that f,.7) where stands for positive semi-definiteness, i.e. f has non-negative eigenvalues. Proposition.4 If f is conve and differentiable, then for all, δ R n, f + δ) f ) + δ f )..8) Remark.5 Equation.8) could also be used to define conveness. However, in the case of non-differentiability the concept of subgradient is required..3. Approimations The following inequalities will be used in the course. The functions are plotted in Figure. for a visual interpretation of these inequalities. ) Upper bound on the eponential function obtained by linearizing e in : e +..9) ) Lower bound on the logarithm function, derived by using the log operator on.9): log + )..) ) This inequality follows from the conveity of fz) = e αz and is obtained by inserting and as evaluation points in.5): e α + e α ) for [, ]..) 3) Finally, a harder inequality: log ) + for [, /]..) Challenge Problem) Logarithm inequality: Prove the inequality.).
3 Lecture : Weighted Majority Algorithm f) = e f) = +. f) = log + ) f) =.8 f).5 f) f) = e 3 f) = + e α ) f) = log ) f) = f) f) Figure.: Plots of the functions in the inequalities.9) -.).
4 Lecture : Weighted Majority Algorithm -4.4 Back to Online Learning The drawback of the Halving algorithm presented last time is the strong assumption that a perfect epert eists. How can this assumption be removed? The answer is to use weights for the eperts, based on past performance. This leads to the Weighted Majority Algorithm WMA) outlined below. This algorithm was first proposed 994 by Littlestone and Warmuth in []. Algorithm : Weighted Majority Algorithm input: N eperts predicting the outcomes, a parameter ɛ >. wi for all i =,..., N weights initialized to for all eperts) for rounds t=,,... do fi t {, } obtain prediction of epert i, i =,..., N) ŷ t round i wt i f i t ) compute prediction of WMA) i wt i Outcome y t is revealed w t+ i w t i ɛ)[f t i y t ] epert weights are updated according to their predictions) end The function round : [, ] {, } above is defined as round) = { if [, /], if /, ]..3) Theorem.6 For all eperts i, it holds that M T WMA) log N ɛ + + ɛ)m T epert i),.4) where M T WMA) resp. M T epert i)) is the number of mistakes of the algorithm resp. epert i) up to round T. Proof Idea: The proof is similar to the that of the bound on the Halving algorithm, but instead of remaining number of eperts, total weight is used. Proof: Define total weight at time t as Evidently, we have that Furthermore, it holds that Φ t = N wi. t.5) i= Φ = N..6) Φ T w T i = ɛ) M T epert i),.7) since the weight of epert i will have been decreased M T epert i) times. Suppose that the algorithm makes a false prediction at time t. Then more than half of the weight Φ t must have been on eperts who made false predictions. Thus, their weight would decrease by a factor ɛ. This leads to the following result: Lemma.7 If the algorithm makes a mistake at time t, the following inequality holds: Φ t+ Φ t ɛ )..8)
5 Lecture : Weighted Majority Algorithm -5 Eercise) Prove this lemma rigorously. By repeatedly applying the lemma, Using.6),.7) and.9) one then obtains Φ T Φ ɛ )M T WMA)..9) ɛ) M T epert i) N ɛ )M T WMA)..) Apply the negative logarithm to get log ɛ) M T epert i) logn) + log ɛ ) }{{} ) M T WMA),.) }{{} ɛ + ɛ ɛ/ where the new inequalities result from using.) and.), respectively. By inserting these and rearranging the terms, the inequality stated in the theorem is derived..5 Net lecture The Weighted Majority Algorithm will be discussed further in the net lecture; a variant of the algorithm will be presented which gets rid of the factor in Theorem.6. References [] Brightwell, G., and Winkler, P. Counting linear etensions is #p-complete. In Proceedings of the twenty-third annual ACM symposium on Theory of computing New York, NY, USA, 99), STOC 9, ACM, pp [] Littlestone, N., and Warmuth, M. The weighted majority algorithm. Information and Computation 8, 994), 6. To use this inequality, ε must be less than.5 or actually.68)
Lecture 16: Perceptron and Exponential Weights Algorithm
EECS 598-005: Theoretical Foundations of Machine Learning Fall 2015 Lecture 16: Perceptron and Exponential Weights Algorithm Lecturer: Jacob Abernethy Scribes: Yue Wang, Editors: Weiqing Yu and Andrew
More information1 Review of Vertex Cover
CS266: Parameterized Algorithms and Complexity Stanford University Lecture 3 Tuesday, April 9 Scribe: Huacheng Yu Spring 2013 1 Review of Vertex Cover In the last lecture, we discussed FPT algorithms for
More informationClassification. Jordan Boyd-Graber University of Maryland WEIGHTED MAJORITY. Slides adapted from Mohri. Jordan Boyd-Graber UMD Classification 1 / 13
Classification Jordan Boyd-Graber University of Maryland WEIGHTED MAJORITY Slides adapted from Mohri Jordan Boyd-Graber UMD Classification 1 / 13 Beyond Binary Classification Before we ve talked about
More informationOnline Convex Optimization
Advanced Course in Machine Learning Spring 2010 Online Convex Optimization Handouts are jointly prepared by Shie Mannor and Shai Shalev-Shwartz A convex repeated game is a two players game that is performed
More informationLecture 19: UCB Algorithm and Adversarial Bandit Problem. Announcements Review on stochastic multi-armed bandit problem
Lecture 9: UCB Algorithm and Adversarial Bandit Problem EECS598: Prediction and Learning: It s Only a Game Fall 03 Lecture 9: UCB Algorithm and Adversarial Bandit Problem Prof. Jacob Abernethy Scribe:
More informationLecture 2: Convex Sets and Functions
Lecture 2: Convex Sets and Functions Hyang-Won Lee Dept. of Internet & Multimedia Eng. Konkuk University Lecture 2 Network Optimization, Fall 2015 1 / 22 Optimization Problems Optimization problems are
More informationLecture 23: Online convex optimization Online convex optimization: generalization of several algorithms
EECS 598-005: heoretical Foundations of Machine Learning Fall 2015 Lecture 23: Online convex optimization Lecturer: Jacob Abernethy Scribes: Vikas Dhiman Disclaimer: hese notes have not been subjected
More informationLecture 23: Conditional Gradient Method
10-725/36-725: Conve Optimization Spring 2015 Lecture 23: Conditional Gradient Method Lecturer: Ryan Tibshirani Scribes: Shichao Yang,Diyi Yang,Zhanpeng Fang Note: LaTeX template courtesy of UC Berkeley
More informationCS 395T Computational Learning Theory. Scribe: Rahul Suri
CS 395T Computational Learning Theory Lecture 6: September 19, 007 Lecturer: Adam Klivans Scribe: Rahul Suri 6.1 Overview In Lecture 5, we showed that for any DNF formula f with n variables and s terms
More informationAlgorithms, Games, and Networks January 17, Lecture 2
Algorithms, Games, and Networks January 17, 2013 Lecturer: Avrim Blum Lecture 2 Scribe: Aleksandr Kazachkov 1 Readings for today s lecture Today s topic is online learning, regret minimization, and minimax
More informationLecture 9: Low Rank Approximation
CSE 521: Design and Analysis of Algorithms I Fall 2018 Lecture 9: Low Rank Approximation Lecturer: Shayan Oveis Gharan February 8th Scribe: Jun Qi Disclaimer: These notes have not been subjected to the
More informationTHE WEIGHTED MAJORITY ALGORITHM
THE WEIGHTED MAJORITY ALGORITHM Csaba Szepesvári University of Alberta CMPUT 654 E-mail: szepesva@ualberta.ca UofA, October 3, 2006 OUTLINE 1 PREDICTION WITH EXPERT ADVICE 2 HALVING: FIND THE PERFECT EXPERT!
More informationLECTURE 3 LECTURE OUTLINE
LECTURE 3 LECTURE OUTLINE Differentiable Conve Functions Conve and A ne Hulls Caratheodory s Theorem Reading: Sections 1.1, 1.2 All figures are courtesy of Athena Scientific, and are used with permission.
More informationLecture 10. ( x domf. Remark 1 The domain of the conjugate function is given by
10-1 Multi-User Information Theory Jan 17, 2012 Lecture 10 Lecturer:Dr. Haim Permuter Scribe: Wasim Huleihel I. CONJUGATE FUNCTION In the previous lectures, we discussed about conve set, conve functions
More information1 Overview. 2 Learning from Experts. 2.1 Defining a meaningful benchmark. AM 221: Advanced Optimization Spring 2016
AM 1: Advanced Optimization Spring 016 Prof. Yaron Singer Lecture 11 March 3rd 1 Overview In this lecture we will introduce the notion of online convex optimization. This is an extremely useful framework
More informationOptimization and Optimal Control in Banach Spaces
Optimization and Optimal Control in Banach Spaces Bernhard Schmitzer October 19, 2017 1 Convex non-smooth optimization with proximal operators Remark 1.1 (Motivation). Convex optimization: easier to solve,
More informationOn a Problem of Alsina Again
Journal of Mathematical Analysis and Applications 54, 67 635 00 doi:0.006 jmaa.000.768, available online at http: www.idealibrary.com on On a Problem of Alsina Again Janusz Matkowski Institute of Mathematics,
More informationLecture 6: September 12
10-725: Optimization Fall 2013 Lecture 6: September 12 Lecturer: Ryan Tibshirani Scribes: Micol Marchetti-Bowick Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer: These notes have not
More information1 Basic Information Theory
ECE 6980 An Algorithmic and Information-Theoretic Toolbo for Massive Data Instructor: Jayadev Acharya Lecture #4 Scribe: Xiao Xu 6th September, 206 Please send errors to 243@cornell.edu and acharya@cornell.edu
More informationLecture : Lovász Theta Body. Introduction to hierarchies.
Strong Relaations for Discrete Optimization Problems 20-27/05/6 Lecture : Lovász Theta Body. Introduction to hierarchies. Lecturer: Yuri Faenza Scribes: Yuri Faenza Recall: stable sets and perfect graphs
More informationLinear Extensions of N-free Orders
Linear Extensions of N-free Orders Stefan Felsner felsner@math.tu-berlin.de Institut für Mathematik Technische Universität Berlin Strasse des 17. Juni 136 D-10623 Berlin, Germany Thibault Manneville tmannevi@clipper.ens.fr
More information= 1 2 x (x 1) + 1 {x} (1 {x}). [t] dt = 1 x (x 1) + O (1), [t] dt = 1 2 x2 + O (x), (where the error is not now zero when x is an integer.
Problem Sheet,. i) Draw the graphs for [] and {}. ii) Show that for α R, α+ α [t] dt = α and α+ α {t} dt =. Hint Split these integrals at the integer which must lie in any interval of length, such as [α,
More informationLecture 23: November 19
10-725/36-725: Conve Optimization Fall 2018 Lecturer: Ryan Tibshirani Lecture 23: November 19 Scribes: Charvi Rastogi, George Stoica, Shuo Li Charvi Rastogi: 23.1-23.4.2, George Stoica: 23.4.3-23.8, Shuo
More informationFrom Batch to Transductive Online Learning
From Batch to Transductive Online Learning Sham Kakade Toyota Technological Institute Chicago, IL 60637 sham@tti-c.org Adam Tauman Kalai Toyota Technological Institute Chicago, IL 60637 kalai@tti-c.org
More informationLecture 5: September 15
10-725/36-725: Convex Optimization Fall 2015 Lecture 5: September 15 Lecturer: Lecturer: Ryan Tibshirani Scribes: Scribes: Di Jin, Mengdi Wang, Bin Deng Note: LaTeX template courtesy of UC Berkeley EECS
More informationLecture 2: Stable Polynomials
Math 270: Geometry of Polynomials Fall 2015 Lecture 2: Stable Polynomials Lecturer: Nikhil Srivastava September 8 Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal
More informationCOS 511: Theoretical Machine Learning. Lecturer: Rob Schapire Lecture 24 Scribe: Sachin Ravi May 2, 2013
COS 5: heoretical Machine Learning Lecturer: Rob Schapire Lecture 24 Scribe: Sachin Ravi May 2, 203 Review of Zero-Sum Games At the end of last lecture, we discussed a model for two player games (call
More informationBregman Divergence and Mirror Descent
Bregman Divergence and Mirror Descent Bregman Divergence Motivation Generalize squared Euclidean distance to a class of distances that all share similar properties Lots of applications in machine learning,
More informationOnline Learning. Jordan Boyd-Graber. University of Colorado Boulder LECTURE 21. Slides adapted from Mohri
Online Learning Jordan Boyd-Graber University of Colorado Boulder LECTURE 21 Slides adapted from Mohri Jordan Boyd-Graber Boulder Online Learning 1 of 31 Motivation PAC learning: distribution fixed over
More informationIntroduction to Machine Learning
Introduction to Machine Learning PAC Learning and VC Dimension Varun Chandola Computer Science & Engineering State University of New York at Buffalo Buffalo, NY, USA chandola@buffalo.edu Chandola@UB CSE
More informationOnline Learning, Mistake Bounds, Perceptron Algorithm
Online Learning, Mistake Bounds, Perceptron Algorithm 1 Online Learning So far the focus of the course has been on batch learning, where algorithms are presented with a sample of training data, from which
More informationLecture 14: Newton s Method
10-725/36-725: Conve Optimization Fall 2016 Lecturer: Javier Pena Lecture 14: Newton s ethod Scribes: Varun Joshi, Xuan Li Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer: These notes
More informationLecture 22: Hyperplane Rounding for Max-Cut SDP
CSCI-B609: A Theorist s Toolkit, Fall 016 Nov 17 Lecture : Hyperplane Rounding for Max-Cut SDP Lecturer: Yuan Zhou Scribe: Adithya Vadapalli 1 Introduction In the previous lectures we had seen the max-cut
More informationLecture 9: SVD, Low Rank Approximation
CSE 521: Design and Analysis of Algorithms I Spring 2016 Lecture 9: SVD, Low Rank Approimation Lecturer: Shayan Oveis Gharan April 25th Scribe: Koosha Khalvati Disclaimer: hese notes have not been subjected
More informationLecture 6: September 19
36-755: Advanced Statistical Theory I Fall 2016 Lecture 6: September 19 Lecturer: Alessandro Rinaldo Scribe: YJ Choe Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer: These notes have
More information1 Review of the Perceptron Algorithm
COS 511: Theoretical Machine Learning Lecturer: Rob Schapire Lecture #15 Scribe: (James) Zhen XIANG April, 008 1 Review of the Perceptron Algorithm In the last few lectures, we talked about various kinds
More informationMistake Bound Model, Halving Algorithm, Linear Classifiers, & Perceptron
Stat 928: Statistical Learning Theory Lecture: 18 Mistake Bound Model, Halving Algorithm, Linear Classifiers, & Perceptron Instructor: Sham Kakade 1 Introduction This course will be divided into 2 parts.
More information1 Ways to Describe a Stochastic Process
purdue university cs 59000-nmc networks & matrix computations LECTURE NOTES David F. Gleich September 22, 2011 Scribe Notes: Debbie Perouli 1 Ways to Describe a Stochastic Process We will use the biased
More information6.4 graphs OF logarithmic FUnCTIOnS
SECTION 6. graphs of logarithmic functions 9 9 learning ObjeCTIveS In this section, ou will: Identif the domain of a logarithmic function. Graph logarithmic functions. 6. graphs OF logarithmic FUnCTIOnS
More information8.1 Polynomial Threshold Functions
CS 395T Computational Learning Theory Lecture 8: September 22, 2008 Lecturer: Adam Klivans Scribe: John Wright 8.1 Polynomial Threshold Functions In the previous lecture, we proved that any function over
More informationOnline Learning Summer School Copenhagen 2015 Lecture 1
Online Learning Summer School Copenhagen 2015 Lecture 1 Shai Shalev-Shwartz School of CS and Engineering, The Hebrew University of Jerusalem Online Learning Shai Shalev-Shwartz (Hebrew U) OLSS Lecture
More information2.1 Laplacian Variants
-3 MS&E 337: Spectral Graph heory and Algorithmic Applications Spring 2015 Lecturer: Prof. Amin Saberi Lecture 2-3: 4/7/2015 Scribe: Simon Anastasiadis and Nolan Skochdopole Disclaimer: hese notes have
More informationOnline Learning with Experts & Multiplicative Weights Algorithms
Online Learning with Experts & Multiplicative Weights Algorithms CS 159 lecture #2 Stephan Zheng April 1, 2016 Caltech Table of contents 1. Online Learning with Experts With a perfect expert Without perfect
More informationA New Lower Bound Technique for Quantum Circuits without Ancillæ
A New Lower Bound Technique for Quantum Circuits without Ancillæ Debajyoti Bera Abstract We present a technique to derive depth lower bounds for quantum circuits. The technique is based on the observation
More information10-725/36-725: Convex Optimization Spring Lecture 21: April 6
10-725/36-725: Conve Optimization Spring 2015 Lecturer: Ryan Tibshirani Lecture 21: April 6 Scribes: Chiqun Zhang, Hanqi Cheng, Waleed Ammar Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer:
More informationMath 410 Linear Algebra Summer Session American River College
Course Information Instructor: Kristin Lui Email: luik@arc.losrios.edu Office Hours: By appointment Location: Liberal Arts 163 ARC Main Campus Meet Times: Tuesday/Thursday 6:30 pm 9:40 pm Dates: June 16,
More informationLearning Theory: Basic Guarantees
Learning Theory: Basic Guarantees Daniel Khashabi Fall 2014 Last Update: April 28, 2016 1 Introduction The Learning Theory 1, is somewhat least practical part of Machine Learning, which is most about the
More informationComputational Learning Theory. Definitions
Computational Learning Theory Computational learning theory is interested in theoretical analyses of the following issues. What is needed to learn effectively? Sample complexity. How many examples? Computational
More informationToday s exercises. 5.17: Football Pools. 5.18: Cells of Line and Hyperplane Arrangements. Inclass: PPZ on the formula F
Exercise Session 9 03.05.2016 slide 1 Today s exercises 5.17: Football Pools 5.18: Cells of Line and Hyperplane Arrangements Inclass: PPZ on the formula F 6.1: Harmonic vs. Geometric Mean 6.2: Many j-isolated
More informationExponential Weights on the Hypercube in Polynomial Time
European Workshop on Reinforcement Learning 14 (2018) October 2018, Lille, France. Exponential Weights on the Hypercube in Polynomial Time College of Information and Computer Sciences University of Massachusetts
More information1.4 FOUNDATIONS OF CONSTRAINED OPTIMIZATION
Essential Microeconomics -- 4 FOUNDATIONS OF CONSTRAINED OPTIMIZATION Fundamental Theorem of linear Programming 3 Non-linear optimization problems 6 Kuhn-Tucker necessary conditions Sufficient conditions
More informationMachine Learning Basics III
Machine Learning Basics III Benjamin Roth CIS LMU München Benjamin Roth (CIS LMU München) Machine Learning Basics III 1 / 62 Outline 1 Classification Logistic Regression 2 Gradient Based Optimization Gradient
More informationAgnostic Online learnability
Technical Report TTIC-TR-2008-2 October 2008 Agnostic Online learnability Shai Shalev-Shwartz Toyota Technological Institute Chicago shai@tti-c.org ABSTRACT We study a fundamental question. What classes
More informationLecture 15: October 15
10-725: Optimization Fall 2012 Lecturer: Barnabas Poczos Lecture 15: October 15 Scribes: Christian Kroer, Fanyi Xiao Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer: These notes have
More informationLecture 7: Dynamic Programming I: Optimal BSTs
5-750: Graduate Algorithms February, 06 Lecture 7: Dynamic Programming I: Optimal BSTs Lecturer: David Witmer Scribes: Ellango Jothimurugesan, Ziqiang Feng Overview The basic idea of dynamic programming
More informationLecture 5: Gradient Descent. 5.1 Unconstrained minimization problems and Gradient descent
10-725/36-725: Convex Optimization Spring 2015 Lecturer: Ryan Tibshirani Lecture 5: Gradient Descent Scribes: Loc Do,2,3 Disclaimer: These notes have not been subjected to the usual scrutiny reserved for
More informationReconstruction. Reading for this lecture: Lecture Notes.
ɛm Reconstruction Reading for this lecture: Lecture Notes. The Learning Channel... ɛ -Machine of a Process: Intrinsic representation! Predictive (or causal) equivalence relation: s s Pr( S S= s ) = Pr(
More informationThe Uniform Hardcore Lemma via Approximate Bregman Projections
The Uniform Hardcore Lemma via Approimate Bregman Projections Boaz Barak Moritz Hardt Satyen Kale Abstract We give a simple, more efficient and uniform proof of the hard-core lemma, a fundamental result
More informationThe Power of Random Counterexamples
Proceedings of Machine Learning Research 76:1 14, 2017 Algorithmic Learning Theory 2017 The Power of Random Counterexamples Dana Angluin DANA.ANGLUIN@YALE.EDU and Tyler Dohrn TYLER.DOHRN@YALE.EDU Department
More informationLecture 4: January 26
10-725/36-725: Conve Optimization Spring 2015 Lecturer: Javier Pena Lecture 4: January 26 Scribes: Vipul Singh, Shinjini Kundu, Chia-Yin Tsai Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer:
More informationLecture 3: September 10
CS294 Markov Chain Monte Carlo: Foundations & Applications Fall 2009 Lecture 3: September 10 Lecturer: Prof. Alistair Sinclair Scribes: Andrew H. Chan, Piyush Srivastava Disclaimer: These notes have not
More informationA note on monotone real circuits
A note on monotone real circuits Pavel Hrubeš and Pavel Pudlák March 14, 2017 Abstract We show that if a Boolean function f : {0, 1} n {0, 1} can be computed by a monotone real circuit of size s using
More information4. Convex Sets and (Quasi-)Concave Functions
4. Convex Sets and (Quasi-)Concave Functions Daisuke Oyama Mathematics II April 17, 2017 Convex Sets Definition 4.1 A R N is convex if (1 α)x + αx A whenever x, x A and α [0, 1]. A R N is strictly convex
More informationLecture 13: Spectral Graph Theory
CSE 521: Design and Analysis of Algorithms I Winter 2017 Lecture 13: Spectral Graph Theory Lecturer: Shayan Oveis Gharan 11/14/18 Disclaimer: These notes have not been subjected to the usual scrutiny reserved
More informationCOS 511: Theoretical Machine Learning. Lecturer: Rob Schapire Lecture #24 Scribe: Jad Bechara May 2, 2018
COS 5: heoretical Machine Learning Lecturer: Rob Schapire Lecture #24 Scribe: Jad Bechara May 2, 208 Review of Game heory he games we will discuss are two-player games that can be modeled by a game matrix
More informationLecture 1: September 25, A quick reminder about random variables and convexity
Information and Coding Theory Autumn 207 Lecturer: Madhur Tulsiani Lecture : September 25, 207 Administrivia This course will cover some basic concepts in information and coding theory, and their applications
More informationMachine Learning and Computational Statistics, Spring 2017 Homework 2: Lasso Regression
Machine Learning and Computational Statistics, Spring 2017 Homework 2: Lasso Regression Due: Monday, February 13, 2017, at 10pm (Submit via Gradescope) Instructions: Your answers to the questions below,
More informationLecture 16: Constraint Satisfaction Problems
A Theorist s Toolkit (CMU 18-859T, Fall 2013) Lecture 16: Constraint Satisfaction Problems 10/30/2013 Lecturer: Ryan O Donnell Scribe: Neal Barcelo 1 Max-Cut SDP Approximation Recall the Max-Cut problem
More informationLecture 7: Schwartz-Zippel Lemma, Perfect Matching. 1.1 Polynomial Identity Testing and Schwartz-Zippel Lemma
CSE 521: Design and Analysis of Algorithms I Winter 2017 Lecture 7: Schwartz-Zippel Lemma, Perfect Matching Lecturer: Shayan Oveis Gharan 01/30/2017 Scribe: Philip Cho Disclaimer: These notes have not
More informationAditya Bhaskara CS 5968/6968, Lecture 1: Introduction and Review 12 January 2016
Lecture 1: Introduction and Review We begin with a short introduction to the course, and logistics. We then survey some basics about approximation algorithms and probability. We also introduce some of
More informationR u t c o r Research R e p o r t. Relations of Threshold and k-interval Boolean Functions. David Kronus a. RRR , April 2008
R u t c o r Research R e p o r t Relations of Threshold and k-interval Boolean Functions David Kronus a RRR 04-2008, April 2008 RUTCOR Rutgers Center for Operations Research Rutgers University 640 Bartholomew
More informationA Necessary Condition for Learning from Positive Examples
Machine Learning, 5, 101-113 (1990) 1990 Kluwer Academic Publishers. Manufactured in The Netherlands. A Necessary Condition for Learning from Positive Examples HAIM SHVAYTSER* (HAIM%SARNOFF@PRINCETON.EDU)
More informationCSC 576: Gradient Descent Algorithms
CSC 576: Gradient Descent Algorithms Ji Liu Department of Computer Sciences, University of Rochester December 22, 205 Introduction The gradient descent algorithm is one of the most popular optimization
More informationCOS 341: Discrete Mathematics
COS 341: Discrete Mathematics Final Exam Fall 2006 Print your name General directions: This exam is due on Monday, January 22 at 4:30pm. Late exams will not be accepted. Exams must be submitted in hard
More informationCS 4407 Algorithms Lecture: Shortest Path Algorithms
CS 440 Algorithms Lecture: Shortest Path Algorithms Prof. Gregory Provan Department of Computer Science University College Cork 1 Outline Shortest Path Problem General Lemmas and Theorems. Algorithms Bellman-Ford
More informationDesign and Analysis of Algorithms
Design and Analysis of Algorithms CSE 5311 Lecture 21 Single-Source Shortest Paths Junzhou Huang, Ph.D. Department of Computer Science and Engineering CSE5311 Design and Analysis of Algorithms 1 Single-Source
More informationLecture 4: Hashing and Streaming Algorithms
CSE 521: Design and Analysis of Algorithms I Winter 2017 Lecture 4: Hashing and Streaming Algorithms Lecturer: Shayan Oveis Gharan 01/18/2017 Scribe: Yuqing Ai Disclaimer: These notes have not been subjected
More informationLimits and Their Properties
Chapter 1 Limits and Their Properties Course Number Section 1.1 A Preview of Calculus Objective: In this lesson you learned how calculus compares with precalculus. I. What is Calculus? (Pages 42 44) Calculus
More informationMath 273a: Optimization Subgradients of convex functions
Math 273a: Optimization Subgradients of convex functions Made by: Damek Davis Edited by Wotao Yin Department of Mathematics, UCLA Fall 2015 online discussions on piazza.com 1 / 20 Subgradients Assumptions
More informationChapter 4 Page 1 of 16. Lecture Guide. Math College Algebra Chapter 4. to accompany. College Algebra by Julie Miller
Chapter 4 Page 1 of 16 Lecture Guide Math 105 - College Algebra Chapter 4 to accompan College Algebra b Julie Miller Corresponding Lecture Videos can be found at Prepared b Stephen Toner & Nichole DuBal
More informationMath 104: Homework 7 solutions
Math 04: Homework 7 solutions. (a) The derivative of f () = is f () = 2 which is unbounded as 0. Since f () is continuous on [0, ], it is uniformly continous on this interval by Theorem 9.2. Hence for
More informationFoundations of Machine Learning On-Line Learning. Mehryar Mohri Courant Institute and Google Research
Foundations of Machine Learning On-Line Learning Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Motivation PAC learning: distribution fixed over time (training and test). IID assumption.
More informationLecture 19: November 10
CS294 Markov Chain Monte Carlo: Foundations & Applications Fall 2009 Lecture 19: November 10 Lecturer: Prof. Alistair Sinclair Scribes: Kevin Dick and Tanya Gordeeva Disclaimer: These notes have not been
More informationAnnouncements. CS 188: Artificial Intelligence Spring Classification. Today. Classification overview. Case-Based Reasoning
CS 188: Artificial Intelligence Spring 21 Lecture 22: Nearest Neighbors, Kernels 4/18/211 Pieter Abbeel UC Berkeley Slides adapted from Dan Klein Announcements On-going: contest (optional and FUN!) Remaining
More informationOutline. Complexity Theory. Introduction. What is abduction? Motivation. Reference VU , SS Logic-Based Abduction
Complexity Theory Complexity Theory Outline Complexity Theory VU 181.142, SS 2018 7. Logic-Based Abduction Reinhard Pichler Institut für Informationssysteme Arbeitsbereich DBAI Technische Universität Wien
More informationROTH S THEOREM THE FOURIER ANALYTIC APPROACH NEIL LYALL
ROTH S THEOREM THE FOURIER AALYTIC APPROACH EIL LYALL Roth s Theorem. Let δ > 0 and ep ep(cδ ) for some absolute constant C. Then any A {0,,..., } of size A = δ necessarily contains a (non-trivial) arithmetic
More informationHomework 4 Solutions
CS 174: Combinatorics and Discrete Probability Fall 01 Homework 4 Solutions Problem 1. (Exercise 3.4 from MU 5 points) Recall the randomized algorithm discussed in class for finding the median of a set
More informationKernel Density Estimation
EECS 598: Statistical Learning Theory, Winter 2014 Topic 19 Kernel Density Estimation Lecturer: Clayton Scott Scribe: Yun Wei, Yanzhen Deng Disclaimer: These notes have not been subjected to the usual
More informationSection 7.2: One-to-One, Onto and Inverse Functions
Section 7.2: One-to-One, Onto and Inverse Functions In this section we shall developed the elementary notions of one-to-one, onto and inverse functions, similar to that developed in a basic algebra course.
More informationSection 1.5 Formal definitions of limits
Section.5 Formal definitions of limits (3/908) Overview: The definitions of the various tpes of limits in previous sections involve phrases such as arbitraril close, sufficientl close, arbitraril large,
More information3.1 Decision Trees Are Less Expressive Than DNFs
CS 395T Computational Complexity of Machine Learning Lecture 3: January 27, 2005 Scribe: Kevin Liu Lecturer: Adam Klivans 3.1 Decision Trees Are Less Expressive Than DNFs 3.1.1 Recap Recall the discussion
More informationWeighted Majority and the Online Learning Approach
Statistical Techniques in Robotics (16-81, F12) Lecture#9 (Wednesday September 26) Weighted Majority and the Online Learning Approach Lecturer: Drew Bagnell Scribe:Narek Melik-Barkhudarov 1 Figure 1: Drew
More informationCS261: Problem Set #3
CS261: Problem Set #3 Due by 11:59 PM on Tuesday, February 23, 2016 Instructions: (1) Form a group of 1-3 students. You should turn in only one write-up for your entire group. (2) Submission instructions:
More informationCSE 431/531: Analysis of Algorithms. Dynamic Programming. Lecturer: Shi Li. Department of Computer Science and Engineering University at Buffalo
CSE 431/531: Analysis of Algorithms Dynamic Programming Lecturer: Shi Li Department of Computer Science and Engineering University at Buffalo Paradigms for Designing Algorithms Greedy algorithm Make a
More informationOnline Submodular Minimization
Online Submodular Minimization Elad Hazan IBM Almaden Research Center 650 Harry Rd, San Jose, CA 95120 hazan@us.ibm.com Satyen Kale Yahoo! Research 4301 Great America Parkway, Santa Clara, CA 95054 skale@yahoo-inc.com
More informationUniversidad Carlos III de Madrid
Universidad Carlos III de Madrid Eercise 1 2 3 4 5 6 Total Points Department of Economics Mathematics I Final Eam January 22nd 2018 LAST NAME: Eam time: 2 hours. FIRST NAME: ID: DEGREE: GROUP: 1 (1) Consider
More informationIS 709/809: Computational Methods in IS Research Fall Exam Review
IS 709/809: Computational Methods in IS Research Fall 2017 Exam Review Nirmalya Roy Department of Information Systems University of Maryland Baltimore County www.umbc.edu Exam When: Tuesday (11/28) 7:10pm
More informationTutorial: Device-independent random number generation. Roger Colbeck University of York
Tutorial: Device-independent random number generation Roger Colbeck University of York Outline Brief motivation of random number generation Discuss what we mean by a random number Discuss some ways of
More informationCSCI-6971 Lecture Notes: Probability theory
CSCI-6971 Lecture Notes: Probability theory Kristopher R. Beevers Department of Computer Science Rensselaer Polytechnic Institute beevek@cs.rpi.edu January 31, 2006 1 Properties of probabilities Let, A,
More informationCS364A: Algorithmic Game Theory Lecture #16: Best-Response Dynamics
CS364A: Algorithmic Game Theory Lecture #16: Best-Response Dynamics Tim Roughgarden November 13, 2013 1 Do Players Learn Equilibria? In this lecture we segue into the third part of the course, which studies
More information