Maximum Likelihood Approach for Symmetric Distribution Property Estimation
|
|
- Caroline Bennett
- 5 years ago
- Views:
Transcription
1 Maximum Likelihood Approach for Symmetric Distribution Property Estimation Jayadev Acharya, Hirakendu Das, Alon Orlitsky, Ananda Suresh Cornell, Yahoo, UCSD, Google
2 Property estimation p: unknown discrete distribution over k elements f(p): a property of p ε: accuracy parameter, δ: error probability Given: access to independent samples from p Goal: estimate f(p) to ±ε with probability > 1 δ Usually, δ constant, say 0.1 Focus of the talk: large k
3 Sample complexity X., X 0,, X 2 : independent samples from p f5(x 2. ): estimate of f(p) Sample complexity of f5(x 2. ): S f5, ε, k, δ = min{n: p, Pr f5(x. 2 ) f(p) ε δ} Sample complexity of f: S f, ε, k, δ = min G 5 S f5, ε, k, δ
4 Symmetric properties Permuting symbol labels does not change f(p) Examples: H p K p K log p K S p K 1 QR ST Renyi entropy, distance to uniformity, unseen symbols, divergences, etc
5 Sequence maximum likelihood N K : # times x appears in X. 2 (multiplicity) p W : empirical distribution p K W = N K n f W X. 2 = f(p W ) Empirical estimators are maximum likelihood estimators p W = arg max Q p(x. 2 ) Call this sequence maximum likelihood (SML)
6 Empirical entropy estimation Empirical estimator: H W X. 2 = H p W = Z N K n log n N K K. S H W, ε, k, 0.1 = Θ k ε Various corrections proposed: Miller-Maddow, Jackknifed estimator, Coverage adjusted, Sample complexity: Ω(k) [Paninski 03]: S H, ε, k, 0.1 = o(k) (existential) Note: For ε 1/k, empirical estimators are the best
7 Entropy estimation [ValiantValiant 11a]: Constructive proofs based on LP: S H, ε, k, 0.1 = Θ c d efg d [YuWang 14, HanJiaoVenkatWeissman 14, ValiantValiant11b]: Simplified algorithms, and exact rates: S H, ε, k, 0.1 = Θ d c efg d
8 Support coverage Expected number of symbols when p is sampled m times S i p = Z(1 1 p K i ) K Goal: Estimate S i p to ±(ε m) [OrlitskySureshWu 16, ZouValiantetal 16]: n = Θ i efg i log ċ samples for δ = 0.1
9 Known results summary Many symmetric properties: entropy, support size, distance to uniform, support coverage Different estimator for each property Sophisticated results from approximation theory
10 Main result Simple, ML based plug-in method that is sample-optimal for entropy, support-coverage, distance to uniform, support size.
11 Profiles Profile of a sequence is the multiset of multiplicities: Φ X. 2 = {N K } X. 2 = 1H, 2T, or X. 2 = 2H, 1T, Φ X. 2 = {1,2} Symmetric properties depend on multiset of probabilities Coins w/ bias 0.4, and 0.6 have same symmetric property Optimal estimators have same output for sequences with same profile. Profiles are sufficient statistic
12 Profile maximum likelihood [OSVZ 04] Probability of a profile: p Φ(X. 2 ) = Z p(y. 2 ) o p q :r o p q sr t p q Maximize the profile probability: X. 2 = 1H, 2T : SML: (2/3, 1/3) PML: (1/2, 1/2) p r uvw = arg max Q p(φ X. 2 )
13 PML for symmetric properties To estimate a symmetric f(p): Find p uvw Φ(X. 2 ) Output f(p uvw ) Advantages: No tuning parameters Not function specific
14 Main result PML is sample-optimal for entropy, support coverage, distance to uniformity, and support size.
15 Ingredients Guarantee for PML. If n = S f, ε, k, δ, then S f p uvw, 2ε, k, δ Wy q.t n If n = S f, ε, k, e }3 n, then S f p PML, 2ε, k, 0. 1 n # profiles of length n < Wy q.t
16 Ingredients n = S f, ε, δ, achieved by an estimator f5(φ(x 2 )): p: underlying distribution. Profiles Φ X 2 such that p Φ X 2 > δ, p uvw Φ p Φ > δ p uvw r Φ p Φ > δ f p r uvw f p f p r uvw f5 Φ + f5 Φ f p < 2ε Profiles with p Φ X 2 < δ, p(p Φ X 2 < δ < δ #profiles of length n
17 Ingredients Better error probability guarantees. Recall: k S H, ε, k, 0.1 = Θ ε log k Stronger error guarantees using McDiarmid s inequality: S H, ε, k, e }2Ž. = Θ d c efg d With twice the samples error drops exponentially Similar results for other properties
18 Main result PML is sample-optimal for entropy, unseen, distance to uniformity, and support size. Even approximate PML is optimal for these.
19 Algorithms EM algorithm [Orlitsky et al] Approximate PML via Bethe Permanents [Vontobel] Extensions of Markov Chains [VatedkaVontobel] Polynomial time algorithms for approximating PML
20 Summary Symmetric property estimation PML plug-in approach Universal, simple to state Independent of particular properties Directions: Efficient algorithms for approximate PML Relies heavily on existence of other estimators
21 In Fisher s words Of course nobody has been able to prove that maximum likelihood estimates are best under all circumstances. Maximum likelihood estimates computed with all the information available may turn out to be inconsistent. Throwing away a substantial part of the information may render them consistent. R. A. Fisher
22 References 1. Acharya, J., Das, H., Orlitsky, A., & Suresh, A. T. (2016). A Unified Maximum Likelihood Approach for Optimal Distribution Property Estimation. arxiv preprint arxiv: Paninski, L. (2003). Estimation of entropy and mutual information. Neural computation, 15(6), Wu, Y., & Yang, P. (2016). Minimax rates of entropy estimation on large alphabets via best polynomial approximation. IEEE Transactions on Information Theory, 62(6), Orlitsky, A., Suresh, A. T., & Wu, Y. (2016). Optimal prediction of the number of unseen species. Proceedings of the National Academy of Sciences, Orlitsky, A., Santhanam, N. P., Viswanathan, K., & Zhang, J. (2004, July). On modeling profiles instead of values. In Proceedings of the 20th conference on Uncertainty in artificial intelligence (pp ). AUAI Press. 6. Valiant, G., & Valiant, P. (2011, June). Estimating the unseen: an n/log (n)-sample estimator for entropy and support size, shown optimal via new CLTs. In Proceedings of the forty-third annual ACM symposium on Theory of computing (pp ). ACM. 7. Jiao, J., Venkat, K., Han, Y., & Weissman, T. (2015). Minimax estimation of functionals of discrete distributions. IEEE Transactions on Information Theory, 61(5), Vatedka, S., & Vontobel, P. O. (2016, July). Pattern maximum likelihood estimation of finite-state discrete-time Markov chains. In Information Theory (ISIT), 2016 IEEE International Symposium on(pp ). IEEE. 9. Vontobel, P. O. (2014, February). The Bethe and Sinkhorn approximations of the pattern maximum likelihood estimate and their connections to the Valiant- Valiant estimate. In Information Theory and Applications Workshop (ITA), 2014(pp. 1-10). IEEE. 10. Valiant, G., & Valiant, P. (2011, October). The power of linear estimators. In Foundations of Computer Science (FOCS), 2011 IEEE 52nd Annual Symposium on (pp ). IEEE. 11. Orlitsky, A., Sajama, S., Santhanam, N. P., Viswanathan, K., & Zhang, J. (2004). Algorithms for modeling distributions over large alphabets. In Information Theory, ISIT Proceedings. International Symposium on (pp ). IEEE.
Estimating Symmetric Distribution Properties Maximum Likelihood Strikes Back!
Estimating Symmetric Distribution Properties Maximum Likelihood Strikes Back! Jayadev Acharya Cornell Hirakendu Das Yahoo Alon Orlitsky UCSD Ananda Suresh Google Shannon Channel March 5, 2018 Based on:
More informationUnified Maximum Likelihood Estimation of Symmetric Distribution Properties
Unified Maximum Likelihood Estimation of Symmetric Distribution Properties Jayadev Acharya HirakenduDas Alon Orlitsky Ananda Suresh Cornell Yahoo UCSD Google Frontiers in Distribution Testing Workshop
More informationInformation Measure Estimation and Applications: Boosting the Effective Sample Size from n to n ln n
Information Measure Estimation and Applications: Boosting the Effective Sample Size from n to n ln n Jiantao Jiao (Stanford EE) Joint work with: Kartik Venkat Yanjun Han Tsachy Weissman Stanford EE Tsinghua
More informationQuantum query complexity of entropy estimation
Quantum query complexity of entropy estimation Xiaodi Wu QuICS, University of Maryland MSR Redmond, July 19th, 2017 J o i n t C e n t e r f o r Quantum Information and Computer Science Outline Motivation
More informationQuadratic-backtracking Algorithm for String Reconstruction from Substring Compositions
Quadratic-backtracking Algorithm for String Reconstruction from Substring Compositions Jayadev Acharya UCSD jacharya@ucsdedu Hirakendu Das Yahoo Labs hdas@yahoo-inccom Olgica Milenkovic UIUC milenkov@uiucedu
More informationSquare Hellinger Subadditivity for Bayesian Networks and its Applications to Identity Testing. Extended Abstract 1
Proceedings of Machine Learning Research vol 65:1 7, 2017 Square Hellinger Subadditivity for Bayesian Networks and its Applications to Identity Testing Constantinos Daskslakis EECS and CSAIL, MIT Qinxuan
More informationdistributed simulation and distributed inference
distributed simulation and distributed inference Algorithms, Tradeoffs, and a Conjecture Clément Canonne (Stanford University) April 13, 2018 Joint work with Jayadev Acharya (Cornell University) and Himanshu
More informationOn the Shamai-Laroia Approximation for the Information Rate of the ISI Channel
On the Shamai-Laroia Approximation for the Information Rate of the ISI Channel Yair Carmon and Shlomo Shamai (Shitz) Department of Electrical Engineering, Technion - Israel Institute of Technology 2014
More informationDoes Better Inference mean Better Learning?
Does Better Inference mean Better Learning? Andrew E. Gelfand, Rina Dechter & Alexander Ihler Department of Computer Science University of California, Irvine {agelfand,dechter,ihler}@ics.uci.edu Abstract
More informationLecture 7 Introduction to Statistical Decision Theory
Lecture 7 Introduction to Statistical Decision Theory I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 20, 2016 1 / 55 I-Hsiang Wang IT Lecture 7
More informationLecture: Aggregation of General Biased Signals
Social Networks and Social Choice Lecture Date: September 7, 2010 Lecture: Aggregation of General Biased Signals Lecturer: Elchanan Mossel Scribe: Miklos Racz So far we have talked about Condorcet s Jury
More informationLecture Learning infinite hypothesis class via VC-dimension and Rademacher complexity;
CSCI699: Topics in Learning and Game Theory Lecture 2 Lecturer: Ilias Diakonikolas Scribes: Li Han Today we will cover the following 2 topics: 1. Learning infinite hypothesis class via VC-dimension and
More informationConvergence Rate of Expectation-Maximization
Convergence Rate of Expectation-Maximiation Raunak Kumar University of British Columbia Mark Schmidt University of British Columbia Abstract raunakkumar17@outlookcom schmidtm@csubcca Expectation-maximiation
More informationCapacity of the Discrete Memoryless Energy Harvesting Channel with Side Information
204 IEEE International Symposium on Information Theory Capacity of the Discrete Memoryless Energy Harvesting Channel with Side Information Omur Ozel, Kaya Tutuncuoglu 2, Sennur Ulukus, and Aylin Yener
More informationProbabilistic Graphical Models for Image Analysis - Lecture 1
Probabilistic Graphical Models for Image Analysis - Lecture 1 Alexey Gronskiy, Stefan Bauer 21 September 2018 Max Planck ETH Center for Learning Systems Overview 1. Motivation - Why Graphical Models 2.
More informationParameter learning in CRF s
Parameter learning in CRF s June 01, 2009 Structured output learning We ish to learn a discriminant (or compatability) function: F : X Y R (1) here X is the space of inputs and Y is the space of outputs.
More informationRecent Results on Input-Constrained Erasure Channels
Recent Results on Input-Constrained Erasure Channels A Case Study for Markov Approximation July, 2017@NUS Memoryless Channels Memoryless Channels Channel transitions are characterized by time-invariant
More informationA brief introduction to Conditional Random Fields
A brief introduction to Conditional Random Fields Mark Johnson Macquarie University April, 2005, updated October 2010 1 Talk outline Graphical models Maximum likelihood and maximum conditional likelihood
More informationTaming Big Probability Distributions
Taming Big Probability Distributions Ronitt Rubinfeld June 18, 2012 CSAIL, Massachusetts Institute of Technology, Cambridge MA 02139 and the Blavatnik School of Computer Science, Tel Aviv University. Research
More informationLiterature on Bregman divergences
Literature on Bregman divergences Lecture series at Univ. Hawai i at Mānoa Peter Harremoës February 26, 2016 Information divergence was introduced by Kullback and Leibler [25] and later Kullback started
More informationUnsupervised Learning with Permuted Data
Unsupervised Learning with Permuted Data Sergey Kirshner skirshne@ics.uci.edu Sridevi Parise sparise@ics.uci.edu Padhraic Smyth smyth@ics.uci.edu School of Information and Computer Science, University
More informationComputational Lower Bounds for Statistical Estimation Problems
Computational Lower Bounds for Statistical Estimation Problems Ilias Diakonikolas (USC) (joint with Daniel Kane (UCSD) and Alistair Stewart (USC)) Workshop on Local Algorithms, MIT, June 2018 THIS TALK
More information3 Finish learning monotone Boolean functions
COMS 6998-3: Sub-Linear Algorithms in Learning and Testing Lecturer: Rocco Servedio Lecture 5: 02/19/2014 Spring 2014 Scribes: Dimitris Paidarakis 1 Last time Finished KM algorithm; Applications of KM
More informationExtending Monte Carlo Methods to Factor Graphs with Negative and Complex Factors
ITW 202 Extending Monte Carlo Methods to Factor Graphs with Negative and Complex Factors Mehdi Molkaraie and Hans-Andrea Loeliger ETH Zurich Dept. of Information Technology & Electrical Engineering 8092
More informationarxiv: v1 [cs.lg] 12 Jul 2017
Aditi Raghunathan 1 Gregory Valiant 1 James Zou 1 2 arxiv:1707.03854v1 [cs.lg] 12 Jul 2017 Abstract Given samples from a distribution, how many new elements should we expect to find if we continue sampling
More informationConvexity/Concavity of Renyi Entropy and α-mutual Information
Convexity/Concavity of Renyi Entropy and -Mutual Information Siu-Wai Ho Institute for Telecommunications Research University of South Australia Adelaide, SA 5095, Australia Email: siuwai.ho@unisa.edu.au
More informationMinimax Optimal Bayes Mixtures for Memoryless Sources over Large Alphabets
Proceedings of Machine Learning Research 8: 8, 208 Algorithmic Learning Theory 208 Minimax Optimal Bayes Mixtures for Memoryless Sources over Large Alphabets Elias Jääsaari Helsinki Institute for Information
More informationInformation, Utility & Bounded Rationality
Information, Utility & Bounded Rationality Pedro A. Ortega and Daniel A. Braun Department of Engineering, University of Cambridge Trumpington Street, Cambridge, CB2 PZ, UK {dab54,pao32}@cam.ac.uk Abstract.
More informationThe Behaviour of the Akaike Information Criterion when Applied to Non-nested Sequences of Models
The Behaviour of the Akaike Information Criterion when Applied to Non-nested Sequences of Models Centre for Molecular, Environmental, Genetic & Analytic (MEGA) Epidemiology School of Population Health
More informationThe Minimum Message Length Principle for Inductive Inference
The Principle for Inductive Inference Centre for Molecular, Environmental, Genetic & Analytic (MEGA) Epidemiology School of Population Health University of Melbourne University of Helsinki, August 25,
More information16.1 Bounding Capacity with Covering Number
ECE598: Information-theoretic methods in high-dimensional statistics Spring 206 Lecture 6: Upper Bounds for Density Estimation Lecturer: Yihong Wu Scribe: Yang Zhang, Apr, 206 So far we have been mostly
More information10 Robotic Exploration and Information Gathering
NAVARCH/EECS 568, ROB 530 - Winter 2018 10 Robotic Exploration and Information Gathering Maani Ghaffari April 2, 2018 Robotic Information Gathering: Exploration and Monitoring In information gathering
More informationNUMERICAL COMPUTATION OF THE CAPACITY OF CONTINUOUS MEMORYLESS CHANNELS
NUMERICAL COMPUTATION OF THE CAPACITY OF CONTINUOUS MEMORYLESS CHANNELS Justin Dauwels Dept. of Information Technology and Electrical Engineering ETH, CH-8092 Zürich, Switzerland dauwels@isi.ee.ethz.ch
More information1 Distribution Property Testing
ECE 6980 An Algorithmic and Information-Theoretic Toolbox for Massive Data Instructor: Jayadev Acharya Lecture #10-11 Scribe: JA 27, 29 September, 2016 Please send errors to acharya@cornell.edu 1 Distribution
More informationLatent Tree Approximation in Linear Model
Latent Tree Approximation in Linear Model Navid Tafaghodi Khajavi Dept. of Electrical Engineering, University of Hawaii, Honolulu, HI 96822 Email: navidt@hawaii.edu ariv:1710.01838v1 [cs.it] 5 Oct 2017
More informationLecture : Probabilistic Machine Learning
Lecture : Probabilistic Machine Learning Riashat Islam Reasoning and Learning Lab McGill University September 11, 2018 ML : Many Methods with Many Links Modelling Views of Machine Learning Machine Learning
More informationRefined Bounds on the Empirical Distribution of Good Channel Codes via Concentration Inequalities
Refined Bounds on the Empirical Distribution of Good Channel Codes via Concentration Inequalities Maxim Raginsky and Igal Sason ISIT 2013, Istanbul, Turkey Capacity-Achieving Channel Codes The set-up DMC
More informationAutomatic Differentiation Equipped Variable Elimination for Sensitivity Analysis on Probabilistic Inference Queries
Automatic Differentiation Equipped Variable Elimination for Sensitivity Analysis on Probabilistic Inference Queries Anonymous Author(s) Affiliation Address email Abstract 1 2 3 4 5 6 7 8 9 10 11 12 Probabilistic
More informationRobust Monte Carlo Methods for Sequential Planning and Decision Making
Robust Monte Carlo Methods for Sequential Planning and Decision Making Sue Zheng, Jason Pacheco, & John Fisher Sensing, Learning, & Inference Group Computer Science & Artificial Intelligence Laboratory
More informationMulti-Attribute Bayesian Optimization under Utility Uncertainty
Multi-Attribute Bayesian Optimization under Utility Uncertainty Raul Astudillo Cornell University Ithaca, NY 14853 ra598@cornell.edu Peter I. Frazier Cornell University Ithaca, NY 14853 pf98@cornell.edu
More informationInformation Complexity vs. Communication Complexity: Hidden Layers Game
Information Complexity vs. Communication Complexity: Hidden Layers Game Jiahui Liu Final Project Presentation for Information Theory in TCS Introduction Review of IC vs CC Hidden Layers Game Upper Bound
More informationOutline of Today s Lecture
University of Washington Department of Electrical Engineering Computer Speech Processing EE516 Winter 2005 Jeff A. Bilmes Lecture 12 Slides Feb 23 rd, 2005 Outline of Today s
More informationVariable selection and feature construction using methods related to information theory
Outline Variable selection and feature construction using methods related to information theory Kari 1 1 Intelligent Systems Lab, Motorola, Tempe, AZ IJCNN 2007 Outline Outline 1 Information Theory and
More informationLecture 3: Lower Bounds for Bandit Algorithms
CMSC 858G: Bandits, Experts and Games 09/19/16 Lecture 3: Lower Bounds for Bandit Algorithms Instructor: Alex Slivkins Scribed by: Soham De & Karthik A Sankararaman 1 Lower Bounds In this lecture (and
More informationIntroduction An approximated EM algorithm Simulation studies Discussion
1 / 33 An Approximated Expectation-Maximization Algorithm for Analysis of Data with Missing Values Gong Tang Department of Biostatistics, GSPH University of Pittsburgh NISS Workshop on Nonignorable Nonresponse
More informationLecture 4 Noisy Channel Coding
Lecture 4 Noisy Channel Coding I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw October 9, 2015 1 / 56 I-Hsiang Wang IT Lecture 4 The Channel Coding Problem
More informationLog-Linear Models, MEMMs, and CRFs
Log-Linear Models, MEMMs, and CRFs Michael Collins 1 Notation Throughout this note I ll use underline to denote vectors. For example, w R d will be a vector with components w 1, w 2,... w d. We use expx
More informationFinding a Needle in a Haystack: Conditions for Reliable. Detection in the Presence of Clutter
Finding a eedle in a Haystack: Conditions for Reliable Detection in the Presence of Clutter Bruno Jedynak and Damianos Karakos October 23, 2006 Abstract We study conditions for the detection of an -length
More information1 Review of The Learning Setting
COS 5: Theoretical Machine Learning Lecturer: Rob Schapire Lecture #8 Scribe: Changyan Wang February 28, 208 Review of The Learning Setting Last class, we moved beyond the PAC model: in the PAC model we
More informationMonte Carlo Methods. Leon Gu CSD, CMU
Monte Carlo Methods Leon Gu CSD, CMU Approximate Inference EM: y-observed variables; x-hidden variables; θ-parameters; E-step: q(x) = p(x y, θ t 1 ) M-step: θ t = arg max E q(x) [log p(y, x θ)] θ Monte
More informationEE/Stats 376A: Homework 7 Solutions Due on Friday March 17, 5 pm
EE/Stats 376A: Homework 7 Solutions Due on Friday March 17, 5 pm 1. Feedback does not increase the capacity. Consider a channel with feedback. We assume that all the recieved outputs are sent back immediately
More informationGraph Matching & Information. Geometry. Towards a Quantum Approach. David Emms
Graph Matching & Information Geometry Towards a Quantum Approach David Emms Overview Graph matching problem. Quantum algorithms. Classical approaches. How these could help towards a Quantum approach. Graphs
More informationNear-Optimal-Sample Estimators for Spherical Gaussian Mixtures
Near-Optimal-Sample Estimators for Spherical Gaussian Mixtures Jayadev Acharya MIT jayadev@mit.edu Ashkan Jafarpour, Alon Orlitsky, Ananda Theertha Suresh UC San Diego {ashkan, alon, asuresh}@ucsd.edu
More informationFrom CDF to PDF A Density Estimation Method for High Dimensional Data
From CDF to PDF A Density Estimation Method for High Dimensional Data Shengdong Zhang Simon Fraser University sza75@sfu.ca arxiv:1804.05316v1 [stat.ml] 15 Apr 2018 April 17, 2018 1 Introduction Probability
More information5 Mutual Information and Channel Capacity
5 Mutual Information and Channel Capacity In Section 2, we have seen the use of a quantity called entropy to measure the amount of randomness in a random variable. In this section, we introduce several
More informationCS 188: Artificial Intelligence Spring Today
CS 188: Artificial Intelligence Spring 2006 Lecture 9: Naïve Bayes 2/14/2006 Dan Klein UC Berkeley Many slides from either Stuart Russell or Andrew Moore Bayes rule Today Expectations and utilities Naïve
More informationAnalyticity and Derivatives of Entropy Rate for HMP s
Analyticity and Derivatives of Entropy Rate for HMP s Guangyue Han University of Hong Kong Brian Marcus University of British Columbia 1 Hidden Markov chains A hidden Markov chain Z = {Z i } is a stochastic
More information3. If a choice is broken down into two successive choices, the original H should be the weighted sum of the individual values of H.
Appendix A Information Theory A.1 Entropy Shannon (Shanon, 1948) developed the concept of entropy to measure the uncertainty of a discrete random variable. Suppose X is a discrete random variable that
More informationApproximating the Partition Function by Deleting and then Correcting for Model Edges (Extended Abstract)
Approximating the Partition Function by Deleting and then Correcting for Model Edges (Extended Abstract) Arthur Choi and Adnan Darwiche Computer Science Department University of California, Los Angeles
More informationEE376A: Homework #3 Due by 11:59pm Saturday, February 10th, 2018
Please submit the solutions on Gradescope. EE376A: Homework #3 Due by 11:59pm Saturday, February 10th, 2018 1. Optimal codeword lengths. Although the codeword lengths of an optimal variable length code
More information1. Principle of large deviations
1. Principle of large deviations This section will provide a short introduction to the Law of large deviations. The basic principle behind this theory centers on the observation that certain functions
More informationLecture 2: August 31
0-704: Information Processing and Learning Fall 206 Lecturer: Aarti Singh Lecture 2: August 3 Note: These notes are based on scribed notes from Spring5 offering of this course. LaTeX template courtesy
More informationPATTERN RECOGNITION AND MACHINE LEARNING
PATTERN RECOGNITION AND MACHINE LEARNING Chapter 1. Introduction Shuai Huang April 21, 2014 Outline 1 What is Machine Learning? 2 Curve Fitting 3 Probability Theory 4 Model Selection 5 The curse of dimensionality
More informationEntropy Accumulation in Device-independent Protocols
Entropy Accumulation in Device-independent Protocols QIP17 Seattle January 19, 2017 arxiv: 1607.01796 & 1607.01797 Rotem Arnon-Friedman, Frédéric Dupuis, Omar Fawzi, Renato Renner, & Thomas Vidick Outline
More informationA Tight Excess Risk Bound via a Unified PAC-Bayesian- Rademacher-Shtarkov-MDL Complexity
A Tight Excess Risk Bound via a Unified PAC-Bayesian- Rademacher-Shtarkov-MDL Complexity Peter Grünwald Centrum Wiskunde & Informatica Amsterdam Mathematical Institute Leiden University Joint work with
More informationCOMP2610/COMP Information Theory
COMP2610/COMP6261 - Information Theory Lecture 9: Probabilistic Inequalities Mark Reid and Aditya Menon Research School of Computer Science The Australian National University August 19th, 2014 Mark Reid
More informationMaximum Likelihood Decoding of Codes on the Asymmetric Z-channel
Maximum Likelihood Decoding of Codes on the Asymmetric Z-channel Pål Ellingsen paale@ii.uib.no Susanna Spinsante s.spinsante@univpm.it Angela Barbero angbar@wmatem.eis.uva.es May 31, 2005 Øyvind Ytrehus
More informationLecture 2: Program Obfuscation - II April 1, 2009
Advanced Topics in Cryptography Lecture 2: Program Obfuscation - II April 1, 2009 Lecturer: S. Goldwasser, M. Naor Scribe by: R. Marianer, R. Rothblum Updated: May 3, 2009 1 Introduction Barak et-al[1]
More informationHomework 1 Due: Wednesday, September 28, 2016
0-704 Information Processing and Learning Fall 06 Homework Due: Wednesday, September 8, 06 Notes: For positive integers k, [k] := {,..., k} denotes te set of te first k positive integers. Wen p and Y q
More informationUniversal Estimation of Divergence for Continuous Distributions via Data-Dependent Partitions
Universal Estimation of for Continuous Distributions via Data-Dependent Partitions Qing Wang, Sanjeev R. Kulkarni, Sergio Verdú Department of Electrical Engineering Princeton University Princeton, NJ 8544
More informationSequence labeling. Taking collective a set of interrelated instances x 1,, x T and jointly labeling them
HMM, MEMM and CRF 40-957 Special opics in Artificial Intelligence: Probabilistic Graphical Models Sharif University of echnology Soleymani Spring 2014 Sequence labeling aking collective a set of interrelated
More information9 Multi-Model State Estimation
Technion Israel Institute of Technology, Department of Electrical Engineering Estimation and Identification in Dynamical Systems (048825) Lecture Notes, Fall 2009, Prof. N. Shimkin 9 Multi-Model State
More informationInformation Divergences and the Curious Case of the Binary Alphabet
Information Divergences and the Curious Case of the Binary Alphabet Jiantao Jiao, Thomas Courtade, Albert No, Kartik Venkat, and Tsachy Weissman Department of Electrical Engineering, Stanford University;
More informationEE5139R: Problem Set 7 Assigned: 30/09/15, Due: 07/10/15
EE5139R: Problem Set 7 Assigned: 30/09/15, Due: 07/10/15 1. Cascade of Binary Symmetric Channels The conditional probability distribution py x for each of the BSCs may be expressed by the transition probability
More informationTHE LIGHT BULB PROBLEM 1
THE LIGHT BULB PROBLEM 1 Ramamohan Paturi 2 Sanguthevar Rajasekaran 3 John Reif 3 Univ. of California, San Diego Univ. of Pennsylvania Duke University 1 Running Title: The Light Bulb Problem Corresponding
More informationmuch more on minimax (order bounds) cf. lecture by Iain Johnstone
much more on minimax (order bounds) cf. lecture by Iain Johnstone http://www-stat.stanford.edu/~imj/wald/wald1web.pdf today s lecture parametric estimation, Fisher information, Cramer-Rao lower bound:
More informationThe sum of d small-bias generators fools polynomials of degree d
The sum of d small-bias generators fools polynomials of degree d Emanuele Viola April 9, 2008 Abstract We prove that the sum of d small-bias generators L : F s F n fools degree-d polynomials in n variables
More informationComputing and Communications 2. Information Theory -Entropy
1896 1920 1987 2006 Computing and Communications 2. Information Theory -Entropy Ying Cui Department of Electronic Engineering Shanghai Jiao Tong University, China 2017, Autumn 1 Outline Entropy Joint entropy
More information+ + ( + ) = Linear recurrent networks. Simpler, much more amenable to analytic treatment E.g. by choosing
Linear recurrent networks Simpler, much more amenable to analytic treatment E.g. by choosing + ( + ) = Firing rates can be negative Approximates dynamics around fixed point Approximation often reasonable
More informationAlgorithmisches Lernen/Machine Learning
Algorithmisches Lernen/Machine Learning Part 1: Stefan Wermter Introduction Connectionist Learning (e.g. Neural Networks) Decision-Trees, Genetic Algorithms Part 2: Norman Hendrich Support-Vector Machines
More informationTesting Distributions Candidacy Talk
Testing Distributions Candidacy Talk Clément Canonne Columbia University 2015 Introduction Introduction Property testing: what can we say about an object while barely looking at it? P 3 / 20 Introduction
More informationModel Selection Tutorial 2: Problems With Using AIC to Select a Subset of Exposures in a Regression Model
Model Selection Tutorial 2: Problems With Using AIC to Select a Subset of Exposures in a Regression Model Centre for Molecular, Environmental, Genetic & Analytic (MEGA) Epidemiology School of Population
More informationIntroduction to Machine Learning Lecture 14. Mehryar Mohri Courant Institute and Google Research
Introduction to Machine Learning Lecture 14 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Density Estimation Maxent Models 2 Entropy Definition: the entropy of a random variable
More informationCOMPSCI 650 Applied Information Theory Jan 21, Lecture 2
COMPSCI 650 Applied Information Theory Jan 21, 2016 Lecture 2 Instructor: Arya Mazumdar Scribe: Gayane Vardoyan, Jong-Chyi Su 1 Entropy Definition: Entropy is a measure of uncertainty of a random variable.
More informationCMU-Q Lecture 24:
CMU-Q 15-381 Lecture 24: Supervised Learning 2 Teacher: Gianni A. Di Caro SUPERVISED LEARNING Hypotheses space Hypothesis function Labeled Given Errors Performance criteria Given a collection of input
More informationStochastic Gradient Estimate Variance in Contrastive Divergence and Persistent Contrastive Divergence
ESANN 0 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 7-9 April 0, idoc.com publ., ISBN 97-7707-. Stochastic Gradient
More informationUsing Expectation-Maximization for Reinforcement Learning
NOTE Communicated by Andrew Barto and Michael Jordan Using Expectation-Maximization for Reinforcement Learning Peter Dayan Department of Brain and Cognitive Sciences, Center for Biological and Computational
More informationDiscrete Mathematics and Probability Theory Fall 2015 Lecture 21
CS 70 Discrete Mathematics and Probability Theory Fall 205 Lecture 2 Inference In this note we revisit the problem of inference: Given some data or observations from the world, what can we infer about
More informationLecture 8: Information Theory and Statistics
Lecture 8: Information Theory and Statistics Part II: Hypothesis Testing and I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 23, 2015 1 / 50 I-Hsiang
More informationMaterial presented. Direct Models for Classification. Agenda. Classification. Classification (2) Classification by machines 6/16/2010.
Material presented Direct Models for Classification SCARF JHU Summer School June 18, 2010 Patrick Nguyen (panguyen@microsoft.com) What is classification? What is a linear classifier? What are Direct Models?
More informationWeighted Finite-State Transducers in Computational Biology
Weighted Finite-State Transducers in Computational Biology Mehryar Mohri Courant Institute of Mathematical Sciences mohri@cims.nyu.edu Joint work with Corinna Cortes (Google Research). 1 This Tutorial
More informationUniversal Loseless Compression: Context Tree Weighting(CTW)
Universal Loseless Compression: Context Tree Weighting(CTW) Dept. Electrical Engineering, Stanford University Dec 9, 2014 Universal Coding with Model Classes Traditional Shannon theory assume a (probabilistic)
More informationEstimating the Unseen: Improved Estimators for Entropy and other Properties
Estimating the : Improved Estimators for Entropy and other Properties Gregory Valiant Stanford University Stanford, CA 9435 valiant@stanford.edu Paul Valiant Brown University Providence, RI 292 pvaliant@gmail.com
More informationThe Complexity of the Permanent and Related Problems
The Complexity of the Permanent and Related Problems Tim Abbott and Alex Schwendner May 9, 2007 Contents 1 The Permanent 2 1.1 Variations on the Determinant...................... 2 1.2 Graph Interpretation...........................
More informationObject Detection Grammars
Object Detection Grammars Pedro F. Felzenszwalb and David McAllester February 11, 2010 1 Introduction We formulate a general grammar model motivated by the problem of object detection in computer vision.
More informationApproximate Nash Equilibria with Near Optimal Social Welfare
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 015) Approximate Nash Equilibria with Near Optimal Social Welfare Artur Czumaj, Michail Fasoulakis, Marcin
More informationAppendices for the article entitled Semi-supervised multi-class classification problems with scarcity of labelled data
Appendices for the article entitled Semi-supervised multi-class classification problems with scarcity of labelled data Jonathan Ortigosa-Hernández, Iñaki Inza, and Jose A. Lozano Contents 1 Appendix A.
More informationAgnostic Learning of Disjunctions on Symmetric Distributions
Agnostic Learning of Disjunctions on Symmetric Distributions Vitaly Feldman vitaly@post.harvard.edu Pravesh Kothari kothari@cs.utexas.edu May 26, 2014 Abstract We consider the problem of approximating
More informationPAC Learning. prof. dr Arno Siebes. Algorithmic Data Analysis Group Department of Information and Computing Sciences Universiteit Utrecht
PAC Learning prof. dr Arno Siebes Algorithmic Data Analysis Group Department of Information and Computing Sciences Universiteit Utrecht Recall: PAC Learning (Version 1) A hypothesis class H is PAC learnable
More informationStochastic Complexity of Variational Bayesian Hidden Markov Models
Stochastic Complexity of Variational Bayesian Hidden Markov Models Tikara Hosino Department of Computational Intelligence and System Science, Tokyo Institute of Technology Mailbox R-5, 459 Nagatsuta, Midori-ku,
More information