Local Differential Privacy
|
|
- Mabel O’Connor’
- 6 years ago
- Views:
Transcription
1 Local Differential Privacy Peter Kairouz Department of Electrical & Computer Engineering University of Illinois at Urbana-Champaign Joint work with Sewoong Oh (UIUC) and Pramod Viswanath (UIUC) / 33
2 Wireless Communication The fundamental limits of digital communication are well understood 2 / 33
3 Rise of the Planet of the Apps! 3 / 33
4 Rise of the Planet of the Apps! 3 / 33
5 Rise of the Planet of the Apps! 3 / 33
6 Rise of the Planet of the Apps! we study the fundamental trade-off between privacy and utility 3 / 33
7 Does Privacy Matter? [Greenwald 204] If you re doing something that you don t want other people to know, maybe you shouldn t be doing it in first place Privacy is no longer a social norm! 4 / 33
8 Recent Privacy Leaks from anonymous faces to social security numbers 5 / 33
9 Recent Privacy Leaks deanonymizing Netflix data 5 / 33
10 Recent Privacy Leaks deanonymizing Netflix data, identifying personal genomes, etc. 5 / 33
11 Privacy is a fundamental human right! 6 / 33
12 The Ultimate Protection The future of privacy is lying randomizing = systematic lying 7 / 33
13 Privacy via Plausible Deniability [Warner 965] Have you ever used illegal drugs? say yes answer truthfully 8 / 33
14 Privacy via Plausible Deniability [Warner 965] Q: privatization mechanism instead of X = x, share Y = y w.p. Q (y x) Q : X Y stochastic mapping 8 / 33
15 The Local Privacy Model [Duchi, et. al., 202] X Privatization Q Y Clients Data Analyst X 2 Privatization Q Y 2 clients receive a service if they share their data clients do not trust data analysts 9 / 33
16 Inference of Information X X = {0, } Privatization Q Y Y X : input alphabet Y: output alphabet Given Y = y and Q, detect whether X = 0 or X = 0 / 33
17 Inference of Information given Y and Q, detect whether X = 0 or X = two types of error: false alarm and missed detection S 0 : ˆX = 0 S : ˆX = Y: output alphabet P FA = P (Y S X = 0) and P MD = P (Y S 0 X = ) 0 / 33
18 Inference of Information Case : Q P FA R P MD 0 / 33
19 Inference of Information Case 2: Q 2 P FA R P MD 0 / 33
20 Inference of Information P FA P FA R R 2 P MD P MD if R 2 R, Q 2 guarantees more privacy 0 / 33
21 Local Differential Privacy (Binary Data) P FA 0.5 e R (ε,δ) e P MD / 33
22 Local Differential Privacy (Binary Data) P FA 0.5 e R (ε,δ) R Q e P MD Q is (ε, δ)-differentially private if R Q R (ε,δ) / 33
23 Local Differential Privacy Q is ε-locally differentially private iff for all x, x X and y Y e ε Q(y x) Q(y x ) eε ε controls the level of privacy ε = more private ε = less private 2 / 33
24 Local Differential Privacy Q is ε-locally differentially private iff for all x, x X P FA P FA + e ε P MD e ε P FA + P MD +e ε R ε R Q +e ε P MD Q is ε-dp iff R Q R ε for all x, x X 2 / 33
25 Privacy vs. Utility the more private you want to be, the less utility you get there is a fundamental trade-off between privacy and utility maximize Q subject to U(Q) Q D ε U(Q): application dependent utility function D ε : set of all ε-locally differentially private mechanisms 3 / 33
26 Summary of Results Binary data: X = 2 The Binary Randomized Response optimal for all ε w.p. +e ε lie w.p. e ε +e ε answer truthfully optimal for all U(Q) obeying the data processing inequality 4 / 33
27 Summary of Results k-ary data: X = k > 2 Binary Mechanism (BM) Randomized Response (RM) Staircase Mechanisms Locally Differentially Private Mechanisms staircase mechanisms are optimal for all ε and a rich class of utilities BM and RR are optimal in the high and low privacy regimes 4 / 33
28 CASE : BINARY DATA 5 / 33
29 Utility Functions U X X Q U (Q) Y Y W U (QW ) Z Z utility functions obeying the data processing inequality: U (QW ) U (Q) U further randomization can only reduce utility note: Q D ε = QW D ε 6 / 33
30 Main Result [Kairouz, et. al., 204] The binary randomized response is optimal P FA 0 e ε +e ε 0 +e ε +e ε e ε +e ε +e ε R QBRR = R ε +e ε P MD = U obeying the data processing inequality: U(Q) U(Q RR ) 7 / 33
31 CASE 2: k-ary DATA 8 / 33
32 Information Theoretic Utility Functions X = k > 2 focus on a rich set of convex utility functions maximize Q subject to U (Q) Q D ε includes all f-divergences, mutual information, etc. 9 / 33
33 Statistical Data Model X ~ P Privatization Q Y ~ M Clients X2 ~ P Privatization Q Y2 ~ M Data Analyst ˆ analyst interested in statistics of data rather than individual samples privatized data: Y i M ν (Y = y) = x X Q(Y = y x)p ν(x = x) 20 / 33
34 Hypothesis Testing X ~ P X ~ P Clients X2 ~ P X2 ~ P Data Analyst ˆ Given {X i } n i=, detect whether ν = 0 or ν = performance is a function of distance between P 0 from P Chernoff-Stein s lemma: P FA e n D kl(p 0 P ) 2 / 33
35 Private Hypothesis Testing X ~ P Privatization Q Y ~ M Clients X2 ~ P Privatization Q Y2 ~ M Data Analyst ˆ {0,} Given {Y i } n i=, detect whether ν = 0 or ν = performance is a function of distance between M 0 from M Chernoff-Stein s lemma: P FA e n D kl(m 0 M ) 22 / 33
36 f-divergences A rich family of measures of differences between distributions: maximize Q subject to D f ( QP }{{} 0 QP }{{} M 0 Q D ε M ) KL divergence D kl (M 0 M ) total variation M 0 M TV minimax rates and error exponents 23 / 33
37 Staircase Mechanisms Recall that: Q is ε-locally differentially private iff for all x, x X and y Y e ε Q(y x) Q(y x ) eε ε controls the level of privacy ε = more private ε = less private 24 / 33
38 Staircase Mechanisms Q is a staircase mechanism if for all x, x X and y Y: Q(y x) Q(y x ) { e ε,, e ε} Binary Mechanism (BM) Randomized Response (RM) Staircase Mechanisms Locally Differentially Private Mechanisms 24 / 33
39 Main Result [Kairouz, et. al., 204] maximize Q D f ( QP }{{} 0 QP ) = maximize }{{} Q M 0 M D f ( QP }{{} 0 QP }{{} M 0 M ) subject to Q D ε subject to Q S ε S ε : set of all staircase mechanisms with Y X staircase mechanisms are optimal no gain in larger output alphabets there are finitely many staircase mechanisms same result holds for a rich set of convex utility functions 25 / 33
40 Binary Mechanisms e ε +e ε y = 0 +e ε x = maps k-ary inputs to binary outputs 26 / 33
41 Binary Mechanisms A deterministic binary mapping followed by a randomized response 0 e ε +e ε 0 X X X S = Ỹ = 0 X S c = Ỹ = Ỹ +e ε +e ε e ε +e ε a highly quantized version of the original data 26 / 33
42 Optimality of Binary Mechanisms (High Privacy) Q B (0 x) = Q B ( x) = { e ε +e if P ε 0 (x) P (x) +e if P ε 0 (x) < P (x) { e ε +e ε if P 0 (x) < P (x) +e ε if P 0 (x) P (x) P 0,P, ε(p 0, P ) > 0 such that ε ε(p 0, P ), Q B is optimal 27 / 33
43 Randomized Response y = e ε 3+e ε 3+e ε x = maps k-ary inputs to k-ary outputs 28 / 33
44 Randomized Response w.p. X X +e ε lie w.p. e ε X +e ε answer truthfully lie = choose another character in X uniformly at random can be viewed as a k-ary extension to the binary randomized response 28 / 33
45 Optimality of Randomized Response (Low Privacy) Q RR (y x) = { e ε X +e ε if y = x X +e ε if y x P 0,P, ε(p 0, P ) > 0 such that ε ε(p 0, P ), Q RR is optimal note that Q RR does not depend on P 0 and P 29 / 33
46 Numerical Example for KL Divergence X = D kl (QP 0 QP ) D kl (Q optp 0 D kl (Q optp ) 0.2 binary mechanism 0. randomized response random pairs of (P 0, P ) ε 30 / 33
47 Numerical Example for KL Divergence X = D kl (QP 0 QP ) D kl (P 0 P ) optimal mechanism binary mechanism randomized response geometric mechanism averaged over 00 random pairs of (P 0, P ) ε 30 / 33
48 Big Picture local differential privacy is crucial for data collection applications we studied a broad class of information theoretic utilities we provided explicit constructions of optimal mechanisms more results on local privacy: Extremal mechanisms for local differential privacy, NIPS 204 The composition theorem for differential privacy, ICML 205 Optimality of non-interactive randomized response, arxiv: / 33
49 Big Picture local differential privacy is crucial for data collection applications we studied a broad class of information theoretic utilities we provided explicit constructions of optimal mechanisms more results on local privacy: Extremal mechanisms for local differential privacy, NIPS 204 The composition theorem for differential privacy, ICML 205 Optimality of non-interactive randomized response, arxiv: / 33
50 Big Picture local differential privacy is crucial for data collection applications we studied a broad class of information theoretic utilities we provided explicit constructions of optimal mechanisms more results on local privacy: Extremal mechanisms for local differential privacy, NIPS 204 The composition theorem for differential privacy, ICML 205 Optimality of non-interactive randomized response, arxiv: / 33
51 Big Picture local differential privacy is crucial for data collection applications we studied a broad class of information theoretic utilities we provided explicit constructions of optimal mechanisms more results on local privacy: Extremal mechanisms for local differential privacy, NIPS 204 The composition theorem for differential privacy, ICML 205 Optimality of non-interactive randomized response, arxiv: / 33
52 Going Forward private green button private genomic data sharing private RAPPOR 32 / 33
53 Thank You Questions? 33 / 33
Extremal Mechanisms for Local Differential Privacy
Extremal Mechanisms for Local Differential Privacy Peter Kairouz Sewoong Oh 2 Pramod Viswanath Department of Electrical & Computer Engineering 2 Department of Industrial & Enterprise Systems Engineering
More informationExtremal Mechanisms for Local Differential Privacy
Journal of Machine Learning Research 7 206-5 Submitted 4/5; Published 4/6 Extremal Mechanisms for Local Differential Privacy Peter Kairouz Department of Electrical and Computer Engineering University of
More informationThe Optimal Mechanism in Differential Privacy
The Optimal Mechanism in Differential Privacy Quan Geng Advisor: Prof. Pramod Viswanath 11/07/2013 PhD Final Exam of Quan Geng, ECE, UIUC 1 Outline Background on Differential Privacy ε-differential Privacy:
More informationDifferentially Private Multi-party Computation
ifferentially Private Multi-party Computation Peter Kairouz, Sewoong Oh, Pramod Viswanath epartment of Electrical and Computer Engineering University of Illinois at Urbana-Champaign {kairouz2, pramodv}@illinois.edu
More informationc 2016 Peter Kairouz
c 206 Peter Kairouz THE FUNDAMENTAL LIMITS OF STATISTICAL DATA PRIVACY BY PETER KAIROUZ DISSERTATION Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Electrical
More informationThe Optimal Mechanism in Differential Privacy
The Optimal Mechanism in Differential Privacy Quan Geng Advisor: Prof. Pramod Viswanath 3/29/2013 PhD Prelimary Exam of Quan Geng, ECE, UIUC 1 Outline Background on differential privacy Problem formulation
More informationUncertainty. Jayakrishnan Unnikrishnan. CSL June PhD Defense ECE Department
Decision-Making under Statistical Uncertainty Jayakrishnan Unnikrishnan PhD Defense ECE Department University of Illinois at Urbana-Champaign CSL 141 12 June 2010 Statistical Decision-Making Relevant in
More informationQuiz 2 Date: Monday, November 21, 2016
10-704 Information Processing and Learning Fall 2016 Quiz 2 Date: Monday, November 21, 2016 Name: Andrew ID: Department: Guidelines: 1. PLEASE DO NOT TURN THIS PAGE UNTIL INSTRUCTED. 2. Write your name,
More informationThe Composition Theorem for Differential Privacy
The Composition Theorem for Differential Privacy Peter Kairouz, Member, IEEE, Sewoong Oh, Member, IEEE, Pramod Viswanath, Fellow, IEEE, Abstract Sequential querying of differentially private mechanisms
More informationLocally Differentially Private Protocols for Frequency Estimation. Tianhao Wang, Jeremiah Blocki, Ninghui Li, Somesh Jha
Locally Differentially Private Protocols for Frequency Estimation Tianhao Wang, Jeremiah Blocki, Ninghui Li, Somesh Jha Differential Privacy Differential Privacy Classical setting Differential Privacy
More informationLecture 8: Information Theory and Statistics
Lecture 8: Information Theory and Statistics Part II: Hypothesis Testing and Estimation I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 22, 2015
More informationSecond-Order Asymptotics in Information Theory
Second-Order Asymptotics in Information Theory Vincent Y. F. Tan (vtan@nus.edu.sg) Dept. of ECE and Dept. of Mathematics National University of Singapore (NUS) National Taiwan University November 2015
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 informationHypothesis Testing under Mutual Information Privacy Constraints in the High Privacy Regime
Hypothesis Testing under Mutual Information Privacy Constraints in the High Privacy Regime Jiachun Liao, Lalitha Sankar, Vincent Y. F. Tan and Flavio du Pin Calmon arxiv:74.8347v [cs.it] 6 Apr 7 Abstract
More informationReport on Differential Privacy
Report on Differential Privacy Lembit Valgma Supervised by Vesal Vojdani December 19, 2017 1 Introduction Over the past decade the collection and analysis of personal data has increased a lot. This has
More informationSHARED INFORMATION. Prakash Narayan with. Imre Csiszár, Sirin Nitinawarat, Himanshu Tyagi, Shun Watanabe
SHARED INFORMATION Prakash Narayan with Imre Csiszár, Sirin Nitinawarat, Himanshu Tyagi, Shun Watanabe 2/40 Acknowledgement Praneeth Boda Himanshu Tyagi Shun Watanabe 3/40 Outline Two-terminal model: Mutual
More informationLecture 22: Error exponents in hypothesis testing, GLRT
10-704: Information Processing and Learning Spring 2012 Lecture 22: Error exponents in hypothesis testing, GLRT Lecturer: Aarti Singh Scribe: Aarti Singh Disclaimer: These notes have not been subjected
More informationToward Distribution Estimation under Local Differential Privacy with Small Samples
Proceedings on Privacy Enhancing Technologies ; 28 (3):84 4 Takao Murakami*, Hideitsu Hino, and Jun Sakuma Toward Distribution Estimation under Local Differential Privacy with Small Samples Abstract: A
More informationSHARED INFORMATION. Prakash Narayan with. Imre Csiszár, Sirin Nitinawarat, Himanshu Tyagi, Shun Watanabe
SHARED INFORMATION Prakash Narayan with Imre Csiszár, Sirin Nitinawarat, Himanshu Tyagi, Shun Watanabe 2/41 Outline Two-terminal model: Mutual information Operational meaning in: Channel coding: channel
More information21.2 Example 1 : Non-parametric regression in Mean Integrated Square Error Density Estimation (L 2 2 risk)
10-704: Information Processing and Learning Spring 2015 Lecture 21: Examples of Lower Bounds and Assouad s Method Lecturer: Akshay Krishnamurthy Scribes: Soumya Batra Note: LaTeX template courtesy of UC
More informationMGMT 69000: Topics in High-dimensional Data Analysis Falll 2016
MGMT 69000: Topics in High-dimensional Data Analysis Falll 2016 Lecture 14: Information Theoretic Methods Lecturer: Jiaming Xu Scribe: Hilda Ibriga, Adarsh Barik, December 02, 2016 Outline f-divergence
More informationMaryam Shoaran Alex Thomo Jens Weber. University of Victoria, Canada
Maryam Shoaran Alex Thomo Jens Weber University of Victoria, Canada Introduction Challenge: Evidence of Participation Sample Aggregates Zero-Knowledge Privacy Analysis of Utility of ZKP Conclusions 12/17/2015
More informationPermuation Models meet Dawid-Skene: A Generalised Model for Crowdsourcing
Permuation Models meet Dawid-Skene: A Generalised Model for Crowdsourcing Ankur Mallick Electrical and Computer Engineering Carnegie Mellon University amallic@andrew.cmu.edu Abstract The advent of machine
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 information[This document is a formalization of personal notes and was created for internal use]
Understanding Statistical and Entropy-Based Image Similarity Measures ISM Sarju Vaz Georgia Institute of Technology, 12-5-2003 [This document is a formalization of personal notes
More informationFrans M.J. Willems. Authentication Based on Secret-Key Generation. Frans M.J. Willems. (joint work w. Tanya Ignatenko)
Eindhoven University of Technology IEEE EURASIP Spain Seminar on Signal Processing, Communication and Information Theory, Universidad Carlos III de Madrid, December 11, 2014 : Secret-Based Authentication
More informationHands-On Learning Theory Fall 2016, Lecture 3
Hands-On Learning Theory Fall 016, Lecture 3 Jean Honorio jhonorio@purdue.edu 1 Information Theory First, we provide some information theory background. Definition 3.1 (Entropy). The entropy of a discrete
More informationCommunication-efficient and Differentially-private Distributed SGD
1/36 Communication-efficient and Differentially-private Distributed SGD Ananda Theertha Suresh with Naman Agarwal, Felix X. Yu Sanjiv Kumar, H. Brendan McMahan Google Research November 16, 2018 2/36 Outline
More informationRAPPOR: Randomized Aggregatable Privacy- Preserving Ordinal Response
RAPPOR: Randomized Aggregatable Privacy- Preserving Ordinal Response Úlfar Erlingsson, Vasyl Pihur, Aleksandra Korolova Google & USC Presented By: Pat Pannuto RAPPOR, What is is good for? (Absolutely something!)
More informationLecture 9: October 25, Lower bounds for minimax rates via multiple hypotheses
Information and Coding Theory Autumn 07 Lecturer: Madhur Tulsiani Lecture 9: October 5, 07 Lower bounds for minimax rates via multiple hypotheses In this lecture, we extend the ideas from the previous
More informationChapter 2. Binary and M-ary Hypothesis Testing 2.1 Introduction (Levy 2.1)
Chapter 2. Binary and M-ary Hypothesis Testing 2.1 Introduction (Levy 2.1) Detection problems can usually be casted as binary or M-ary hypothesis testing problems. Applications: This chapter: Simple hypothesis
More informationOn Computational Thinking, Inferential Thinking and Data Science
On Computational Thinking, Inferential Thinking and Data Science Michael I. Jordan University of California, Berkeley December 17, 2016 A Job Description, circa 2015 Your Boss: I need a Big Data system
More informationLecture 17: Density Estimation Lecturer: Yihong Wu Scribe: Jiaqi Mu, Mar 31, 2016 [Ed. Apr 1]
ECE598: Information-theoretic methods in high-dimensional statistics Spring 06 Lecture 7: Density Estimation Lecturer: Yihong Wu Scribe: Jiaqi Mu, Mar 3, 06 [Ed. Apr ] In last lecture, we studied the minimax
More informationPr[X = s Y = t] = Pr[X = s] Pr[Y = t]
Homework 4 By: John Steinberger Problem 1. Recall that a real n n matrix A is positive semidefinite if A is symmetric and x T Ax 0 for all x R n. Assume A is a real n n matrix. Show TFAE 1 : (a) A is positive
More informationLecture 11- Differential Privacy
6.889 New Developments in Cryptography May 3, 2011 Lecture 11- Differential Privacy Lecturer: Salil Vadhan Scribes: Alan Deckelbaum and Emily Shen 1 Introduction In class today (and the next two lectures)
More informationIntroduction to Statistical Learning Theory
Introduction to Statistical Learning Theory In the last unit we looked at regularization - adding a w 2 penalty. We add a bias - we prefer classifiers with low norm. How to incorporate more complicated
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 informationAsymptotically Truthful Equilibrium Selection in Large Congestion Games
Asymptotically Truthful Equilibrium Selection in Large Congestion Games Ryan Rogers - Penn Aaron Roth - Penn June 12, 2014 Related Work Large Games Roberts and Postlewaite 1976 Immorlica and Mahdian 2005,
More informationTowards a Systematic Analysis of Privacy Definitions
Towards a Systematic Analysis of Privacy Definitions Bing-Rong Lin and Daniel Kifer Department of Computer Science & Engineering, Pennsylvania State University, {blin,dkifer}@cse.psu.edu Abstract In statistical
More informationChannel Polarization and Blackwell Measures
Channel Polarization Blackwell Measures Maxim Raginsky Abstract The Blackwell measure of a binary-input channel (BIC is the distribution of the posterior probability of 0 under the uniform input distribution
More informationOn Composite Quantum Hypothesis Testing
University of York 7 November 207 On Composite Quantum Hypothesis Testing Mario Berta Department of Computing with Fernando Brandão and Christoph Hirche arxiv:709.07268 Overview Introduction 2 Composite
More information21.1 Lower bounds on minimax risk for functional estimation
ECE598: Information-theoretic methods in high-dimensional statistics Spring 016 Lecture 1: Functional estimation & testing Lecturer: Yihong Wu Scribe: Ashok Vardhan, Apr 14, 016 In this chapter, we will
More informationLittlestone s Dimension and Online Learnability
Littlestone s Dimension and Online Learnability Shai Shalev-Shwartz Toyota Technological Institute at Chicago The Hebrew University Talk at UCSD workshop, February, 2009 Joint work with Shai Ben-David
More informationDeterministic Finite Automata. Non deterministic finite automata. Non-Deterministic Finite Automata (NFA) Non-Deterministic Finite Automata (NFA)
Deterministic Finite Automata Non deterministic finite automata Automata we ve been dealing with have been deterministic For every state and every alphabet symbol there is exactly one move that the machine
More informationNecessary and Sufficient Conditions for High-Dimensional Salient Feature Subset Recovery
Necessary and Sufficient Conditions for High-Dimensional Salient Feature Subset Recovery Vincent Tan, Matt Johnson, Alan S. Willsky Stochastic Systems Group, Laboratory for Information and Decision Systems,
More informationCMPUT651: Differential Privacy
CMPUT65: Differential Privacy Homework assignment # 2 Due date: Apr. 3rd, 208 Discussion and the exchange of ideas are essential to doing academic work. For assignments in this course, you are encouraged
More informationInt er net Saf et y Tip s
BE CAREFUL AS: Facebook oft en means People oft en pret end t o be people t hey are not so be wary of t his!! Int er net Saf et y Tip s N ever accept people you do not know. Never give out your real name
More informationRoberts Theorem with Neutrality. A Social Welfare Ordering Approach
: A Social Welfare Ordering Approach Indian Statistical Institute joint work with Arunava Sen, ISI Outline Objectives of this research Characterize (dominant strategy) implementable social choice functions
More informationApproximate and Probabilistic Differential Privacy Definitions
pproximate and Probabilistic Differential Privacy Definitions Sebastian Meiser University College London, United Kingdom, e-mail: s.meiser@ucl.ac.uk July 20, 208 bstract This technical report discusses
More informationDetection theory 101 ELEC-E5410 Signal Processing for Communications
Detection theory 101 ELEC-E5410 Signal Processing for Communications Binary hypothesis testing Null hypothesis H 0 : e.g. noise only Alternative hypothesis H 1 : signal + noise p(x;h 0 ) γ p(x;h 1 ) Trade-off
More informationPrivacy and Fault-Tolerance in Distributed Optimization. Nitin Vaidya University of Illinois at Urbana-Champaign
Privacy and Fault-Tolerance in Distributed Optimization Nitin Vaidya University of Illinois at Urbana-Champaign Acknowledgements Shripad Gade Lili Su argmin x2x SX i=1 i f i (x) Applications g f i (x)
More informationPrivacy of Numeric Queries Via Simple Value Perturbation. The Laplace Mechanism
Privacy of Numeric Queries Via Simple Value Perturbation The Laplace Mechanism Differential Privacy A Basic Model Let X represent an abstract data universe and D be a multi-set of elements from X. i.e.
More informationHypothesis Testing with Communication Constraints
Hypothesis Testing with Communication Constraints Dinesh Krithivasan EECS 750 April 17, 2006 Dinesh Krithivasan (EECS 750) Hyp. testing with comm. constraints April 17, 2006 1 / 21 Presentation Outline
More informationConvergence Rate of Markov Chains
Convergence Rate of Markov Chains Will Perkins April 16, 2013 Convergence Last class we saw that if X n is an irreducible, aperiodic, positive recurrent Markov chain, then there exists a stationary distribution
More informationAsymptotically Optimal Quickest Change Detection in Distributed Sensor Systems
This article was downloaded by: [University of Illinois at Urbana-Champaign] On: 23 May 2012, At: 16:03 Publisher: Taylor & Francis Informa Ltd Registered in England and Wales Registered Number: 1072954
More informationCorrelation Detection and an Operational Interpretation of the Rényi Mutual Information
Correlation Detection and an Operational Interpretation of the Rényi Mutual Information Masahito Hayashi 1, Marco Tomamichel 2 1 Graduate School of Mathematics, Nagoya University, and Centre for Quantum
More informationCS 229: Lecture 7 Notes
CS 9: Lecture 7 Notes Scribe: Hirsh Jain Lecturer: Angela Fan Overview Overview of today s lecture: Hypothesis Testing Total Variation Distance Pinsker s Inequality Application of Pinsker s Inequality
More informationLecture 5. 1 Review (Pairwise Independence and Derandomization)
6.842 Randomness and Computation September 20, 2017 Lecture 5 Lecturer: Ronitt Rubinfeld Scribe: Tom Kolokotrones 1 Review (Pairwise Independence and Derandomization) As we discussed last time, we can
More informationEcon 2148, spring 2019 Statistical decision theory
Econ 2148, spring 2019 Statistical decision theory Maximilian Kasy Department of Economics, Harvard University 1 / 53 Takeaways for this part of class 1. A general framework to think about what makes a
More informationReconstruction in the Sparse Labeled Stochastic Block Model
Reconstruction in the Sparse Labeled Stochastic Block Model Marc Lelarge 1 Laurent Massoulié 2 Jiaming Xu 3 1 INRIA-ENS 2 INRIA-Microsoft Research Joint Centre 3 University of Illinois, Urbana-Champaign
More informationRumor Source Obfuscation on Irregular Trees
Rumor Source Obfuscation on Irregular Trees Giulia Fanti University of Illinois at Urbana-Champaign fanti@illinois.edu Kannan Ramchandran University of California, Berkeley kannanr@eecs.berkeley.edu Peter
More information11. Learning graphical models
Learning graphical models 11-1 11. Learning graphical models Maximum likelihood Parameter learning Structural learning Learning partially observed graphical models Learning graphical models 11-2 statistical
More informationData-Efficient Quickest Change Detection
Data-Efficient Quickest Change Detection Venu Veeravalli ECE Department & Coordinated Science Lab University of Illinois at Urbana-Champaign http://www.ifp.illinois.edu/~vvv (joint work with Taposh Banerjee)
More informationScalable robust hypothesis tests using graphical models
Scalable robust hypothesis tests using graphical models Umamahesh Srinivas ipal Group Meeting October 22, 2010 Binary hypothesis testing problem Random vector x = (x 1,...,x n ) R n generated from either
More informationChapter 8: Differential entropy. University of Illinois at Chicago ECE 534, Natasha Devroye
Chapter 8: Differential entropy Chapter 8 outline Motivation Definitions Relation to discrete entropy Joint and conditional differential entropy Relative entropy and mutual information Properties AEP for
More informationLecture 21: Minimax Theory
Lecture : Minimax Theory Akshay Krishnamurthy akshay@cs.umass.edu November 8, 07 Recap In the first part of the course, we spent the majority of our time studying risk minimization. We found many ways
More informationECE598: Information-theoretic methods in high-dimensional statistics Spring 2016
ECE598: Information-theoretic methods in high-dimensional statistics Spring 06 Lecture : Mutual Information Method Lecturer: Yihong Wu Scribe: Jaeho Lee, Mar, 06 Ed. Mar 9 Quick review: Assouad s lemma
More informationSecure Multiparty Computation from Graph Colouring
Secure Multiparty Computation from Graph Colouring Ron Steinfeld Monash University July 2012 Ron Steinfeld Secure Multiparty Computation from Graph Colouring July 2012 1/34 Acknowledgements Based on joint
More informationProof. We indicate by α, β (finite or not) the end-points of I and call
C.6 Continuous functions Pag. 111 Proof of Corollary 4.25 Corollary 4.25 Let f be continuous on the interval I and suppose it admits non-zero its (finite or infinite) that are different in sign for x tending
More informationNoisy-Channel Coding
Copyright Cambridge University Press 2003. On-screen viewing permitted. Printing not permitted. http://www.cambridge.org/05264298 Part II Noisy-Channel Coding Copyright Cambridge University Press 2003.
More information10-704: Information Processing and Learning Fall Lecture 24: Dec 7
0-704: Information Processing and Learning Fall 206 Lecturer: Aarti Singh Lecture 24: Dec 7 Note: These notes are based on scribed notes from Spring5 offering of this course. LaTeX template courtesy of
More informationImproved Spectrum Utilization in Cognitive Radio Systems
Improved Spectrum Utilization in Cognitive Radio Systems Lei Cao and Ramanarayanan Viswanathan Department of Electrical Engineering The University of Mississippi Jan. 15, 2014 Lei Cao and Ramanarayanan
More informationUni- and Bivariate Power
Uni- and Bivariate Power Copyright 2002, 2014, J. Toby Mordkoff Note that the relationship between risk and power is unidirectional. Power depends on risk, but risk is completely independent of power.
More informationInformation Recovery from Pairwise Measurements: A Shannon-Theoretic Approach
Information Recovery from Pairwise Measurements: A Shannon-Theoretic Approach Yuxin Chen Statistics Stanford University Email: yxchen@stanfordedu Changho Suh EE KAIST Email: chsuh@kaistackr Andrea J Goldsmith
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 informationReinforcement Learning
Reinforcement Learning Lecture 6: RL algorithms 2.0 Alexandre Proutiere, Sadegh Talebi, Jungseul Ok KTH, The Royal Institute of Technology Objectives of this lecture Present and analyse two online algorithms
More informationThe Method of Types and Its Application to Information Hiding
The Method of Types and Its Application to Information Hiding Pierre Moulin University of Illinois at Urbana-Champaign www.ifp.uiuc.edu/ moulin/talks/eusipco05-slides.pdf EUSIPCO Antalya, September 7,
More informationCheap talk theoretic tools for distributed sensing in the presence of strategic sensors
1 / 37 Cheap talk theoretic tools for distributed sensing in the presence of strategic sensors Cédric Langbort Department of Aerospace Engineering & Coordinated Science Laboratory UNIVERSITY OF ILLINOIS
More informationDecentralized Detection In Wireless Sensor Networks
Decentralized Detection In Wireless Sensor Networks Milad Kharratzadeh Department of Electrical & Computer Engineering McGill University Montreal, Canada April 2011 Statistical Detection and Estimation
More informationRobust Statistics, Revisited
Robust Statistics, Revisited Ankur Moitra (MIT) joint work with Ilias Diakonikolas, Jerry Li, Gautam Kamath, Daniel Kane and Alistair Stewart CLASSIC PARAMETER ESTIMATION Given samples from an unknown
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 7 Approximate
More informationProblem 1: Compactness (12 points, 2 points each)
Final exam Selected Solutions APPM 5440 Fall 2014 Applied Analysis Date: Tuesday, Dec. 15 2014, 10:30 AM to 1 PM You may assume all vector spaces are over the real field unless otherwise specified. Your
More informationBregman Divergences for Data Mining Meta-Algorithms
p.1/?? Bregman Divergences for Data Mining Meta-Algorithms Joydeep Ghosh University of Texas at Austin ghosh@ece.utexas.edu Reflects joint work with Arindam Banerjee, Srujana Merugu, Inderjit Dhillon,
More informationOn Computational Thinking, Inferential Thinking and Data Science
On Computational Thinking, Inferential Thinking and Data Science Michael I. Jordan University of California, Berkeley September 24, 2016 What Is the Big Data Phenomenon? Science in confirmatory mode (e.g.,
More informationGame Theory and its Applications to Networks - Part I: Strict Competition
Game Theory and its Applications to Networks - Part I: Strict Competition Corinne Touati Master ENS Lyon, Fall 200 What is Game Theory and what is it for? Definition (Roger Myerson, Game Theory, Analysis
More informationPair Hidden Markov Models
Pair Hidden Markov Models Scribe: Rishi Bedi Lecturer: Serafim Batzoglou January 29, 2015 1 Recap of HMMs alphabet: Σ = {b 1,...b M } set of states: Q = {1,..., K} transition probabilities: A = [a ij ]
More informationString Matching. Thanks to Piotr Indyk. String Matching. Simple Algorithm. for s 0 to n-m. Match 0. for j 1 to m if T[s+j] P[j] then
String Matching Thanks to Piotr Indyk String Matching Input: Two strings T[1 n] and P[1 m], containing symbols from alphabet Σ Goal: find all shifts 0 s n-m such that T[s+1 s+m]=p Example: Σ={,a,b,,z}
More informationConvex Analysis and Economic Theory Winter 2018
Division of the Humanities and Social Sciences Ec 181 KC Border Convex Analysis and Economic Theory Winter 2018 Topic 0: Vector spaces 0.1 Basic notation Here are some of the fundamental sets and spaces
More informationBlind Attacks on Machine Learners
Blind Attacks on Machine Learners Alex Beatson 1 Zhaoran Wang 1 Han Liu 1 1 Princeton University NIPS, 2016/ Presenter: Anant Kharkar NIPS, 2016/ Presenter: Anant Kharkar 1 Outline 1 Introduction Motivation
More informationDifferentially Private Real-time Data Release over Infinite Trajectory Streams
Differentially Private Real-time Data Release over Infinite Trajectory Streams Kyoto University, Japan Department of Social Informatics Yang Cao, Masatoshi Yoshikawa 1 Outline Motivation: opportunity &
More informationPrinciples of Coded Modulation. Georg Böcherer
Principles of Coded Modulation Georg Böcherer Contents. Introduction 9 2. Digital Communication System 2.. Transmission System............................. 2.2. Figures of Merit................................
More informationCourse Notes for EE227C (Spring 2018): Convex Optimization and Approximation
Course Notes for EE7C (Spring 08): Convex Optimization and Approximation Instructor: Moritz Hardt Email: hardt+ee7c@berkeley.edu Graduate Instructor: Max Simchowitz Email: msimchow+ee7c@berkeley.edu October
More informationOn the Impossibility of Black-Box Truthfulness Without Priors
On the Impossibility of Black-Box Truthfulness Without Priors Nicole Immorlica Brendan Lucier Abstract We consider the problem of converting an arbitrary approximation algorithm for a singleparameter social
More informationIntroduction to Machine Learning
Introduction to Machine Learning Thomas G. Dietterich tgd@eecs.oregonstate.edu 1 Outline What is Machine Learning? Introduction to Supervised Learning: Linear Methods Overfitting, Regularization, and the
More informationThe Gibbard random dictatorship theorem: a generalization and a new proof
SERIEs (2011) 2:515 527 DOI 101007/s13209-011-0041-z ORIGINAL ARTICLE The Gibbard random dictatorship theorem: a generalization and a new proof Arunava Sen Received: 24 November 2010 / Accepted: 10 January
More informationStatistical Inference with Monotone Incomplete Multivariate Normal Data
Statistical Inference with Monotone Incomplete Multivariate Normal Data p. 1/4 Statistical Inference with Monotone Incomplete Multivariate Normal Data This talk is based on joint work with my wonderful
More informationLecture 12 November 3
STATS 300A: Theory of Statistics Fall 2015 Lecture 12 November 3 Lecturer: Lester Mackey Scribe: Jae Hyuck Park, Christian Fong Warning: These notes may contain factual and/or typographic errors. 12.1
More informationA FEW E-COMMERCE APPLICATIONS. CIS 400/628 Spring 2005 Introduction to Cryptography. This is based on Chapter 9 of Trappe and Washington
A FEW E-COMMERCE APPLICATIONS CIS 400/628 Spring 2005 Introduction to Cryptography This is based on Chapter 9 of Trappe and Washington E-COMMERCE: SET SET = Secure Electronic Transaction Consider a credit
More informationPerformance Estimates of the Pseudo-Random Method for Radar Detection
1 Performance Estimates of the Pseudo-Random Method for Radar Detection Alexander Fish and Shamgar Gurevich Abstract A performance of the pseudo-random method for the radar detection is analyzed. The radar
More informationLecture 3: Empirical Risk Minimization
Lecture 3: Empirical Risk Minimization Introduction to Learning and Analysis of Big Data Kontorovich and Sabato (BGU) Lecture 3 1 / 11 A more general approach We saw the learning algorithms Memorize and
More information