Multiobjective Prediction with Expert Advice



Similar documents
E0 370 Statistical Learning Theory Lecture 20 (Nov 17, 2011)

Mathematics in Pharmacokinetics What and Why (A second attempt to make it clearer)

Niche Market or Mass Market?

Prediction With Expert Advice For The Brier Game

Parameter-Free Convex Learning through Coin Betting

SPEC model selection algorithm for ARCH models: an options pricing evaluation framework

An Online Learning-based Framework for Tracking

arxiv: v2 [cs.lg] 27 Jun 2008

TEMPORAL PATTERN IDENTIFICATION OF TIME SERIES DATA USING PATTERN WAVELETS AND GENETIC ALGORITHMS

ANALYSIS AND COMPARISONS OF SOME SOLUTION CONCEPTS FOR STOCHASTIC PROGRAMMING PROBLEMS

MTH6121 Introduction to Mathematical Finance Lesson 5

AP Calculus AB 2013 Scoring Guidelines

17 Laplace transform. Solving linear ODE with piecewise continuous right hand sides

How To Predict A Person'S Behavior

A Probability Density Function for Google s stocks

Universal Algorithms for Probability Forecasting

AP Calculus AB 2007 Scoring Guidelines

Chapter 13. Network Flow III Applications Edge disjoint paths Edge-disjoint paths in a directed graphs

Stochastic Optimal Control Problem for Life Insurance

Follow the Leader If You Can, Hedge If You Must

Duration and Convexity ( ) 20 = Bond B has a maturity of 5 years and also has a required rate of return of 10%. Its price is $613.

Optimal Investment and Consumption Decision of Family with Life Insurance

The Transport Equation

Longevity 11 Lyon 7-9 September 2015

DYNAMIC MODELS FOR VALUATION OF WRONGFUL DEATH PAYMENTS

Chapter 7. Response of First-Order RL and RC Circuits

Analysis of Pricing and Efficiency Control Strategy between Internet Retailer and Conventional Retailer

Random Walk in 1-D. 3 possible paths x vs n. -5 For our random walk, we assume the probabilities p,q do not depend on time (n) - stationary

Bayesian Filtering with Online Gaussian Process Latent Variable Models

Planning Demand and Supply in a Supply Chain. Forecasting and Aggregate Planning

MACROECONOMIC FORECASTS AT THE MOF A LOOK INTO THE REAR VIEW MIRROR

Task is a schedulable entity, i.e., a thread

Education's Purpose. Faculty

Algorithms for Portfolio Management based on the Newton Method

ON THE PRICING OF EQUITY-LINKED LIFE INSURANCE CONTRACTS IN GAUSSIAN FINANCIAL ENVIRONMENT

An Optimal Selling Strategy for Stock Trading Based on Predicting the Maximum Price

An Online Portfolio Selection Algorithm with Regret Logarithmic in Price Variation

On Learning Algorithms for Nash Equilibria

Class One: Degree Sequences

Forecasting Sales: A Model and Some Evidence from the Retail Industry. Russell Lundholm Sarah McVay Taylor Randall

How To Find Out If You Can Get A Better Esimaion From A Recipe Card

Option Put-Call Parity Relations When the Underlying Security Pays Dividends

The Real Business Cycle paradigm. The RBC model emphasizes supply (technology) disturbances as the main source of

Stochastic Calculus and Option Pricing

Mixability is Bayes Risk Curvature Relative to Log Loss

Answer, Key Homework 2 David McIntyre Mar 25,

The Application of Multi Shifts and Break Windows in Employees Scheduling

Time Consisency in Porfolio Managemen

Chapter 4: Exponential and Logarithmic Functions

Online Convex Programming and Generalized Infinitesimal Gradient Ascent

Performance Center Overview. Performance Center Overview 1

Time Series Analysis Using SAS R Part I The Augmented Dickey-Fuller (ADF) Test

Stock Price Prediction Using the ARIMA Model

Keldysh Formalism: Non-equilibrium Green s Function

Improper Integrals. Dr. Philippe B. laval Kennesaw State University. September 19, f (x) dx over a finite interval [a, b].

The Advantages and Disadvantages of Online Linear Optimization

On the degrees of irreducible factors of higher order Bernoulli polynomials

Chapter 8 Student Lecture Notes 8-1

arxiv: v1 [stat.ml] 23 Sep 2013

A New Adaptive Ensemble Boosting Classifier for Concept Drifting Stream Data

SOLUTIONS FOR PROBLEM SET 2

Working Paper On the timing option in a futures contract. SSE/EFI Working Paper Series in Economics and Finance, No. 619

DELTA-GAMMA-THETA HEDGING OF CRUDE OIL ASIAN OPTIONS

2.4 Network flows. Many direct and indirect applications telecommunication transportation (public, freight, railway, air, ) logistics

An Optimal Strategy of Natural Hedging for. a General Portfolio of Insurance Companies

Optimal Withdrawal Strategies for Retirees with Multiple Savings Accounts

Forecasting and Information Sharing in Supply Chains Under Quasi-ARMA Demand

Cost-Sensitive Learning by Cost-Proportionate Example Weighting

MODEL AND ALGORITHMS FOR THE REAL TIME MANAGEMENT OF RESIDENTIAL ELECTRICITY DEMAND. A. Barbato, G. Carpentieri

TOOL OUTSOURCING RISK RESEARCH BASED ON BP NEURAL NETWORK

The Kinetics of the Stock Markets

Premium indexing in lifelong health insurance

Risk Modelling of Collateralised Lending

The Heisenberg group and Pansu s Theorem

A Note on Using the Svensson procedure to estimate the risk free rate in corporate valuation

1. y 5y + 6y = 2e t Solution: Characteristic equation is r 2 5r +6 = 0, therefore r 1 = 2, r 2 = 3, and y 1 (t) = e 2t,

An accurate analytical approximation for the price of a European-style arithmetic Asian option

Forecasting stock indices: a comparison of classification and level estimation models

Behavior Analysis of a Biscuit Making Plant using Markov Regenerative Modeling

Transcription:

Muliobjecive Predicion wih Exper Advice Alexey Chernov Compuer Learning Research Cenre and Deparmen of Compuer Science Royal Holloway Universiy of London GTP Workshop, June 2010 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 1 / 18

Example: Predicion of Spor Mach Oucome V. Vovk, F. Zhdanov. Predicions wih Exper Advice for Brier Game. ICML 08 Bookmakers daa: 4 bookmakers, odds for 10000 ennis maches (2 oucomes) 8 bookmakers, odds for 9000 fooball maches (3 oucomes) Odds a i can be ransformed o probabiliies Prob[i]: Prob[i] = 1/a i j 1/a j The loss is measured by he square (Brier) loss funcion. Learner s sraegy is he Aggregaing Algorihm. Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 2 / 18

Tennis Predicion, Square Loss 16 14 12 Theoreical bounds Learner Bookmakers 10 8 6 4 2 0 2 4 0 2000 4000 6000 8000 10000 12000 Graph of he negaive regre Loss Ek (T ) Loss(T ), 4 Expers Learner is he AA for he square loss Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 3 / 18

Tennis Predicion, Log Loss 25 20 Theoreical bounds Learner Bookmakers 15 10 5 0 5 0 2000 4000 6000 8000 10000 12000 Graph of he negaive regre Loss Ek (T ) Loss(T ), 4 Expers Learner is he AA for he log loss (Bayes mixure) Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 4 / 18

Tennis Predicions: Wrong Losses Graphs of he negaive regre Loss Ek (T ) Loss(T ) 25 20 Theoreical bounds Learner Bookmakers 15 Theoreical bounds Learner Bookmakers 15 10 10 5 5 0 0 5 10 0 2000 4000 6000 8000 10000 12000 log loss he AA for he square loss Learner opimizes for a wrong loss funcion 5 0 2000 4000 6000 8000 10000 12000 square loss he AA for he log loss Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 5 / 18

Aggregaing Algorihm wih Wrong Losses Fac For he game wih 2 oucomes, one can consruc a sequence of predicions of 2 Expers and a sequence of oucomes wih he following propery. If Learner s predicions are generaed by he Aggregaing Algorihm for he log loss hen for almos all T Loss(T ) Loss E1 (T ) + T /10, where Loss(T ) and Loss E1 (T ) are he square losses of Learner and Exper 1. A similar saemen holds for he Aggregaing Algorihm for he square loss evaluaed by he log loss. Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 6 / 18

New Seings Many loss funcions Expers: γ (1),..., γ (k) Learner: γ Realiy: ω Loss (m) E k (T ) = T =1 λ (m) (γ (k), ω ) T Loss (m) (T ) = λ (m) (γ, ω ) =1 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 7 / 18

New Seings Expers: γ (1),..., γ (k) Learner: γ Realiy: ω Many loss funcions Loss (m) E k (T ) = T =1 λ (m) (γ (k), ω ) Exper Evaluaor s advice Loss (k) E k (T ) = T =1 λ (k) (γ (k), ω ) T Loss (m) (T ) = λ (m) (γ, ω ) =1 T Loss (k) (T ) = λ (k) (γ, ω ) =1 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 7 / 18

Bound for New Seings Theorem If λ (k) are η (k) -mixable proper loss funcions, k = 1,..., K, Learner has a sraegy (e. g. he Defensive Forecasing algorihm) ha guaranees, for all T and for all k, ha Corollary Loss (k) (T ) Loss (k) E k (T ) + 1 ln K. η (k) If λ (m) are η (m) -mixable proper loss funcions, m = 1,..., M, Learner has a sraegy ha guaranees, for all T, for all k and for all m, ha Loss (m) (T ) Loss (m) E k (T ) + 1 (ln K + ln M). η (m) Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 8 / 18

Tennis Predicions, Two Losses Graphs of he negaive regre Loss (m) E k (T ) Loss (m) (T ) 16 14 12 Theoreical bounds Learner Bookmakers 25 20 Theoreical bounds Learner Bookmakers 10 15 8 6 10 4 2 5 0 0 2 4 0 2000 4000 6000 8000 10000 12000 square loss 5 0 2000 4000 6000 8000 10000 12000 log loss Learner opimizes for boh loss funcions, using he DF algorihm. Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 9 / 18

Defensive Forecasing Algorihm π ω K k=1 where p (k) 1 = p(k) 0 eη(loss( 1) Loss E k ( 1)) p (k) 1 eη(λ(π,ω) λ(π(k),ω)) 1, To ge his (from Levin s Lemma) we need ha λ(π, ω) is coninuous and for all π, π E π e η(λ(π, ) λ(π, )) = ω Ω π(ω)e η(λ(π,ω) λ(π,ω)) 1 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 10 / 18

Defensive Forecasing Algorihm π ω K k=1 p (k) 1 eη(k) (λ (k) (π,ω) λ (k) (π (k),ω)) 1, where p (k) 1 = eη(k) p(k) (Loss (k) ( 1) Loss (k) E ( 1)) k 0 To ge his (from Levin s Lemma) we need ha λ (k) (π, ω) is coninuous and for all π, π E π e η(k) (λ (k) (π, ) λ (k) (π, )) = ω Ω π(ω)e η(k) (λ (k) (π,ω) λ (k) (π,ω)) 1 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 10 / 18

The DFA and he AA λ is coninuous and π, π E π e η(λ(π, ) λ(π, )) 1 λ is η-mixable λ is η-mixable and? π, π E π e η(λ(π, ) λ(π, )) 1 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 11 / 18

The DFA and he AA λ is coninuous and π, π E π e η(λ(π, ) λ(π, )) 1 λ is η-mixable π, π E π e η(λ(π, ) λ(π, )) 1 λ is proper λ is η-mixable and proper π, π E π e η(λ(π, ) λ(π, )) 1 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 11 / 18

Proper Loss Funcions λ is proper if for any π, π P(Ω) E π λ(π, ) E π λ(π, ) If ω π hen E π λ(π, ω) is he expeced loss for predicion π. The expeced loss is minimal for he rue disribuion he forecaser is encouraged o give he rue probabiliies The square loss and he log loss are proper. Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 12 / 18

Example: Hellinger Loss λ Hellinger (γ, ω) = 1 2 r ( ) 2 γ(j) I {ω=j} j=1 The Hellinger loss is 2-mixable The Hellinger loss is no proper Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 13 / 18

Proper Mixable Loss Funcions Each mixable loss funcion λ(γ, ω) has a proper analogue λ proper (π, ω) such ha 1 π γ ω λ proper (π, ω) = λ(γ, ω) 2 π γ E π λ proper (π, ) E π λ(γ, ) Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 14 / 18

Proper Mixable Loss Funcions Each mixable loss funcion λ(γ, ω) has a proper analogue λ proper (π, ω) such ha 1 π γ ω λ proper (π, ω) = λ(γ, ω) 2 π γ E π λ proper (π, ) E π λ(γ, ) For he Hellinger loss, he proper analogue is he spherical loss λ spherical (π, ω) = 1 π(ω) r j=1 (π(j))2 λ spherical (π, ω) = λ Hellinger (γ, ω) for γ(ω) = P (π(ω))2 r j=1 (π(j))2 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 14 / 18

Example: Mixable and Non-Mixable Losses Expers 1,..., K predic π (k) P({0, 1}). Expers 1,..., N predic γ (n) {0, 1}. Learner predics (π, π) P({0, 1}) P({0, 1}) such ha if π(0) > 1/2 hen π(0) = 1 and if π(1) > 1/2 hen π(1) = 1. There exiss a sraegy for Learner ha guaranees for any k T λ square (π, ω ) =1 and for any m T λ abs ( π, ω ) =1 T =1 T =1 λ square (π (k), ω ) + ln(k + N) λ simple (γ (n), ω ) + O( T ln(k + N) + T ln ln T ) Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 15 / 18

Tennis Predicions, Square and Absolue Losses Graphs of he negaive regre Loss (m) E k (T ) Loss (m) (T ) 2 1.5 1 heoreical bounds DF expers 0.5 0 DF expers 0.5 0 0.5 0.5 1 1 1.5 1.5 2 2.5 0 50 100 150 200 250 300 350 400 square loss 2 0 50 100 150 200 250 300 350 400 absolue loss Learner opimizes for boh loss funcions, using he DF algorihm wih mixabiliy and Hoeffding supermaringales. Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 16 / 18

The Mixed Supermaringale 1 K + N K k=1 e 2P T 1 + 1 K + N =1 ((p ω ) 2 (p (k) N n=1 1/e 0 η dη ( ln 1 η ω ) 2) e 2((p ω)2 (p (k) where p = π (1), p (k) = π (k) (1), p = π (1). [x y] = 1 if x y and [x y] = 0 if x = y. T ω)2 ) ) 2 e ηp T 1 =1 ( p ω [γ (n) ω ]) η 2 /2 e η( p ω [γ(n) T ω]) η2 /2 Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 17 / 18

References V. Vovk, F. Zhdanov. Predicions wih Exper Advice for Brier Game. ICML 2008. hp://arxiv.org/abs/0710.0485 A. Chernov, Y. Kalnishkan, F. Zhdanov, V. Vovk. Supermaringales in Predicion wih Exper Advice. ALT 2008 and TCS. hp://arxiv.org/abs/1003.2218 A. Chernov, V. Vovk. Predicion wih exper evaluaors advice. ALT 2009. hp://arxiv.org/abs/0902.4127 A. Chernov, V. Vovk. Predicion wih Advice of Unknown Number of Expers. UAI 2010. hp://arxiv.org/abs/1006.0475 hp://onlinepredicion.ne/ Alexey Chernov (RHUL) Muliobjecive Predicion wih Exper Advice GTP Workshop, June 2010 18 / 18