SlideShare a Scribd company logo
A Generalization of Nonparametric Estimation and On-Line
Prediction for Stationary Ergodic Sources
Joe Suzuki
Osaka University
October 23, 2010
AWE6
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 1 / 12
Universal Coding for Finite Sources
Pn: unknown stationary ergodic
 
Find Qn
.
s.t. ∑
xn
Qn
(xn
) ≤ 1
1
n
log
Pn(xn)
Qn(xn)
→ 0
for any Xn ∼ Pn with prob. one.
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 2 / 12
Universal Coding for Continuous Sources
f n: unknown i.i,d. density function with Xi (Ω) ⊆ [0, 1)
 
Level 0: A0 = {[0, 1/2), [1/2, 1)} consisting of two bins
Level 1: A1 = {[0, 1/4), [1/4, 1/2), [1/2, 3/4), [3/4, 1)} of 4 bins
. . . . . .
Level i: Ai = {[0, 1/2i ), [1/2i , 2/2i ), · · · , [(2i − 1)/2i , 1)} of 2i+1 bins
. . . . . .
Find Qi for each i to obtain
gn
(xn
) :=
∞∑
i=0
ωi
Qi (xn)
λi (xn)
1
n
log
f n(xn)
gn(xn)
→ 0
for any Xn ∼ f n with prob. one.
B. Ryabko. IEEE Trans. on Information Theory, VOL. 55, NO. 9, 2009.
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 3 / 12
What if no density function exists ?
For example, if
∫ ∞
0 h(x)dx = 1
FX (x) =



0 x < −1,
1
2 , −1 ≤ x < 0∫ x
0
1
2 h(t)dt, 0 ≤ x
no fX exists s.t. FX (x) =
∫ x
−∞ fX (t)dt.
 
Random variable X in (Ω, F, µ)
Any measurable function X : Ω → R w.r.t. F:
D ∈ B =⇒ {ω ∈ Ω|X(ω) ∈ D} ∈ F
B: the Borel set of R
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 4 / 12
The Radon-Nykodim Theorem
µ is absolutely continuous w.r.t. ν (µ << ν)
.
.
.
ν(A) = 0 =⇒ µ(A) = 0
Radon-Nykodim derivative
dµ
dν
.
.
µ << ν =⇒ ∃g s.t. µ(A) =
∫
A
g(ω)dν(ω)
Finite Sources with prob. P, Q =⇒
dµ
dν
(xn
) =
P(xn)
Q(xn)
Continuous Sources with Density Functions f , g =⇒
dµ
dν
(xn
) =
f (xn)
g(xn)
∃fX =
dF
dx
of FX (x) = µ(X(ω) ≤ x) ⇐⇒ µ << λ
λ: the Lebesgue measure on R
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 5 / 12
Our Goal
µn: unknown stationary ergodic
Find νn
.
.
s.t.
νn
(Xn
(Ω)) ≤ 1
1
n
log
dµn
dνn
(xn
) → 0
for any Xn ∼ µn with prob. one.
 
Such a generalization contains as special cases
finite sources
continuous sources with density functions
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 6 / 12
Ryabko’s Measure: Construction
{Ai }∞
i=0: sequence of finite sets Ai (Ai+1: a refinment of Ai )
si : R → Ai : the projection to Ai
 
Qn
i (a1, · · · , an) , a1, · · · , an ∈ Ai (via finite universal coding)
gn
i (x1, · · · , xn) :=
Qn
i (si (x1), · · · , si (xn)
λn
i (si (x1), · · · , si (xn))
, x1, · · · , xn ∈ R
λn
i (a1, · · · , an): The Lebesgue measure of (a1, · · · , an) ∈ An
i
{ωi }∞
i=0:
∞∑
i=0
ωi = 1, ωi > 0
gn
(x1, · · · , xn) :=
∞∑
i=0
ωi gn
i (x1, · · · , xn)
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 7 / 12
Ryabko’s Measure: Universality
si (Xn) ∼ Pn
i
f n
i (x1, · · · , xn) :=
Pn
i (si (x1), · · · , si (xn))
λn
i (si (x1), · · · , si (xn))
Differential entropy
.
.
h(f ∞
) := lim
n→∞
−
1
n
∫
f n
(xn
) log f n
(xn
)
Ryabko, 2009
If h(f ∞
i ) = h(f ∞) as i → ∞,
then for any stationary ergodic f ∞, with prob. one,
1
n
log
f n(x1, · · · , xn)
gn(x1, · · · , xn)
→ 0
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 8 / 12
Proposed Measure: Construction
{Xn}∞
n=1 ∼ µ∞
 
ηn: µn << ηn (ηn = λn =⇒ Ryabko)
 
For (D1, · · · , Dn) ∈ Bn,
νn
i (D1, · · · , Dn) :=
∑
a1,··· ,an∈Ai
ηn(a1 ∩ D1, · · · , an ∩ Dn)
ηn(a1, · · · , an)
Qn
i (a1, · · · , an) .
 
{ωi }∞
i=0:
∞∑
i=0
ωi = 1, ωi > 0
νn
(D1, · · · , Dn) :=
∞∑
i=0
ωi νn
i (D1, · · · , Dn)
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 9 / 12
Proposed Measure: Property
si (Xn) ∼ Pn
i
µn
i (D1, · · · , Dn) :=
∑
a1,··· ,an∈Ai
ηn(a1 ∩ D1, · · · , an ∩ Dn)
ηn(a1, · · · , an)
Pn
i (a1, · · · , an) .
Kullback-Leibler Information
.
.
D(µn
||ηn
) :=
∫
dµn
log
dµn
dηn
Theorem
If D(µ∞
i ||η∞) = D(µ∞||η∞) as i → ∞,
then for any stationary ergodic µ∞, with prob. one,
1
n
log
dµn
dνn
(x1, · · · , xn) → 0
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 10 / 12
Examples
ex. 1 Ω := [0, 1), η = λ
A0 := {[0, 1/2), [1/2, 1)}
A1 := {[0, 1/4), [1/4, 1/2), [1/2, 3/4), [3/4, 1)}
· · ·
 
ex. 2. Ω := N = {1, 2, · · · }, η(j) =
1
j
−
1
j + 1
, j ∈ N
A0 := {{1}, N − {1}}
A1 := {{1}, {2}, N − {1, 2}}
· · ·
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 11 / 12
Conclusion
Ryabko’s Histogram Weighing and its Extension
.
.
The generalization was succeeded.
Many applications.
Direction: The MDL/Bayesian for Continuous Sources
.
Which is better between νn
1 and νn
2 given observation xn ?
=⇒ evaluate
dνn
1
dνn
2
(xn
).
Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 12 / 12

More Related Content

What's hot

What's hot (20)

WITMSE 2013
WITMSE 2013WITMSE 2013
WITMSE 2013
 
Continuous and Discrete-Time Analysis of SGD
Continuous and Discrete-Time Analysis of SGDContinuous and Discrete-Time Analysis of SGD
Continuous and Discrete-Time Analysis of SGD
 
A
AA
A
 
Multilinear Twisted Paraproducts
Multilinear Twisted ParaproductsMultilinear Twisted Paraproducts
Multilinear Twisted Paraproducts
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
RuFiDiM
RuFiDiMRuFiDiM
RuFiDiM
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
Testing for mixtures by seeking components
Testing for mixtures by seeking componentsTesting for mixtures by seeking components
Testing for mixtures by seeking components
 
A new axisymmetric finite element
A new axisymmetric finite elementA new axisymmetric finite element
A new axisymmetric finite element
 
Scattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysisScattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysis
 
Thesis defense
Thesis defenseThesis defense
Thesis defense
 
Hyperfunction method for numerical integration and Fredholm integral equation...
Hyperfunction method for numerical integration and Fredholm integral equation...Hyperfunction method for numerical integration and Fredholm integral equation...
Hyperfunction method for numerical integration and Fredholm integral equation...
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operatorsA T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
 
On Twisted Paraproducts and some other Multilinear Singular Integrals
On Twisted Paraproducts and some other Multilinear Singular IntegralsOn Twisted Paraproducts and some other Multilinear Singular Integrals
On Twisted Paraproducts and some other Multilinear Singular Integrals
 
Tales on two commuting transformations or flows
Tales on two commuting transformations or flowsTales on two commuting transformations or flows
Tales on two commuting transformations or flows
 
Trilinear embedding for divergence-form operators
Trilinear embedding for divergence-form operatorsTrilinear embedding for divergence-form operators
Trilinear embedding for divergence-form operators
 
Paraproducts with general dilations
Paraproducts with general dilationsParaproducts with general dilations
Paraproducts with general dilations
 
2013 IEEE International Symposium on Information Theory
2013 IEEE International Symposium on Information Theory2013 IEEE International Symposium on Information Theory
2013 IEEE International Symposium on Information Theory
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 

Similar to A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary Ergodic Sources

02-VariableLengthCodes_pres.pdf
02-VariableLengthCodes_pres.pdf02-VariableLengthCodes_pres.pdf
02-VariableLengthCodes_pres.pdf
JunZhao68
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
Hiroshi Kuwajima
 

Similar to A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary Ergodic Sources (20)

IROS 2011 talk 2 (Filippo's file)
IROS 2011 talk 2 (Filippo's file)IROS 2011 talk 2 (Filippo's file)
IROS 2011 talk 2 (Filippo's file)
 
2014 9-16
2014 9-162014 9-16
2014 9-16
 
2014 9-22
2014 9-222014 9-22
2014 9-22
 
Bayesian network structure estimation based on the Bayesian/MDL criteria when...
Bayesian network structure estimation based on the Bayesian/MDL criteria when...Bayesian network structure estimation based on the Bayesian/MDL criteria when...
Bayesian network structure estimation based on the Bayesian/MDL criteria when...
 
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
Slides: On the Chi Square and Higher-Order Chi Distances for Approximating f-...
 
Introduction to Stochastic calculus
Introduction to Stochastic calculusIntroduction to Stochastic calculus
Introduction to Stochastic calculus
 
Slides: Total Jensen divergences: Definition, Properties and k-Means++ Cluste...
Slides: Total Jensen divergences: Definition, Properties and k-Means++ Cluste...Slides: Total Jensen divergences: Definition, Properties and k-Means++ Cluste...
Slides: Total Jensen divergences: Definition, Properties and k-Means++ Cluste...
 
Proba stats-r1-2017
Proba stats-r1-2017Proba stats-r1-2017
Proba stats-r1-2017
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
 
Optimal interval clustering: Application to Bregman clustering and statistica...
Optimal interval clustering: Application to Bregman clustering and statistica...Optimal interval clustering: Application to Bregman clustering and statistica...
Optimal interval clustering: Application to Bregman clustering and statistica...
 
Refresher probabilities-statistics
Refresher probabilities-statisticsRefresher probabilities-statistics
Refresher probabilities-statistics
 
Basics of probability in statistical simulation and stochastic programming
Basics of probability in statistical simulation and stochastic programmingBasics of probability in statistical simulation and stochastic programming
Basics of probability in statistical simulation and stochastic programming
 
02-VariableLengthCodes_pres.pdf
02-VariableLengthCodes_pres.pdf02-VariableLengthCodes_pres.pdf
02-VariableLengthCodes_pres.pdf
 
HPWFcorePRES--FUR2016
HPWFcorePRES--FUR2016HPWFcorePRES--FUR2016
HPWFcorePRES--FUR2016
 
Accelerated reconstruction of a compressively sampled data stream
Accelerated reconstruction of a compressively sampled data streamAccelerated reconstruction of a compressively sampled data stream
Accelerated reconstruction of a compressively sampled data stream
 
Chapter-4 combined.pptx
Chapter-4 combined.pptxChapter-4 combined.pptx
Chapter-4 combined.pptx
 
Finance Enginering from Columbia.pdf
Finance Enginering from Columbia.pdfFinance Enginering from Columbia.pdf
Finance Enginering from Columbia.pdf
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
 
Stochastic Differentiation
Stochastic DifferentiationStochastic Differentiation
Stochastic Differentiation
 
Existence Theory for Second Order Nonlinear Functional Random Differential Eq...
Existence Theory for Second Order Nonlinear Functional Random Differential Eq...Existence Theory for Second Order Nonlinear Functional Random Differential Eq...
Existence Theory for Second Order Nonlinear Functional Random Differential Eq...
 

More from Joe Suzuki

分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減する分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減する
Joe Suzuki
 
離散と連続の入り混じった相互情報量を推定して、 SNP と遺伝子発現量の因果関係をさぐる
離散と連続の入り混じった相互情報量を推定して、SNP と遺伝子発現量の因果関係をさぐる離散と連続の入り混じった相互情報量を推定して、SNP と遺伝子発現量の因果関係をさぐる
離散と連続の入り混じった相互情報量を推定して、 SNP と遺伝子発現量の因果関係をさぐる
Joe Suzuki
 

More from Joe Suzuki (20)

RとPythonを比較する
RとPythonを比較するRとPythonを比較する
RとPythonを比較する
 
R集会@統数研
R集会@統数研R集会@統数研
R集会@統数研
 
E-learning Development of Statistics and in Duex: Practical Approaches and Th...
E-learning Development of Statistics and in Duex: Practical Approaches and Th...E-learning Development of Statistics and in Duex: Practical Approaches and Th...
E-learning Development of Statistics and in Duex: Practical Approaches and Th...
 
分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減する分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減する
 
連続変量を含む条件付相互情報量の推定
連続変量を含む条件付相互情報量の推定連続変量を含む条件付相互情報量の推定
連続変量を含む条件付相互情報量の推定
 
E-learning Design and Development for Data Science in Osaka University
E-learning Design and Development for Data Science in Osaka UniversityE-learning Design and Development for Data Science in Osaka University
E-learning Design and Development for Data Science in Osaka University
 
UAI 2017
UAI 2017UAI 2017
UAI 2017
 
AMBN2017 サテライトワークショップ
AMBN2017 サテライトワークショップAMBN2017 サテライトワークショップ
AMBN2017 サテライトワークショップ
 
CRAN Rパッケージ BNSLの概要
CRAN Rパッケージ BNSLの概要CRAN Rパッケージ BNSLの概要
CRAN Rパッケージ BNSLの概要
 
Forest Learning from Data
Forest Learning from DataForest Learning from Data
Forest Learning from Data
 
A Bayesian Approach to Data Compression
A Bayesian Approach to Data CompressionA Bayesian Approach to Data Compression
A Bayesian Approach to Data Compression
 
研究紹介(学生向け)
研究紹介(学生向け)研究紹介(学生向け)
研究紹介(学生向け)
 
Efficietly Learning Bayesian Network Structures based on the B&B Strategy: A ...
Efficietly Learning Bayesian Network Structuresbased on the B&B Strategy: A ...Efficietly Learning Bayesian Network Structuresbased on the B&B Strategy: A ...
Efficietly Learning Bayesian Network Structures based on the B&B Strategy: A ...
 
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
 
2016 7-13
2016 7-132016 7-13
2016 7-13
 
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
 
連続変量を含む相互情報量の推定
連続変量を含む相互情報量の推定連続変量を含む相互情報量の推定
連続変量を含む相互情報量の推定
 
Jeffreys' and BDeu Priors for Model Selection
Jeffreys' and BDeu Priors for Model SelectionJeffreys' and BDeu Priors for Model Selection
Jeffreys' and BDeu Priors for Model Selection
 
離散と連続の入り混じった相互情報量を推定して、 SNP と遺伝子発現量の因果関係をさぐる
離散と連続の入り混じった相互情報量を推定して、SNP と遺伝子発現量の因果関係をさぐる離散と連続の入り混じった相互情報量を推定して、SNP と遺伝子発現量の因果関係をさぐる
離散と連続の入り混じった相互情報量を推定して、 SNP と遺伝子発現量の因果関係をさぐる
 
MaCaulay2 Miuraパッケージの開発と今後
MaCaulay2 Miuraパッケージの開発と今後MaCaulay2 Miuraパッケージの開発と今後
MaCaulay2 Miuraパッケージの開発と今後
 

Recently uploaded

Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
AADYARAJPANDEY1
 
Anemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditionsAnemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditions
muralinath2
 
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCINGRNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
AADYARAJPANDEY1
 
Aerodynamics. flippatterncn5tm5ttnj6nmnynyppt
Aerodynamics. flippatterncn5tm5ttnj6nmnynypptAerodynamics. flippatterncn5tm5ttnj6nmnynyppt
Aerodynamics. flippatterncn5tm5ttnj6nmnynyppt
sreddyrahul
 
Mammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also FunctionsMammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also Functions
YOGESH DOGRA
 

Recently uploaded (20)

NuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final versionNuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final version
 
Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
 
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of LipidsGBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
 
electrochemical gas sensors and their uses.pptx
electrochemical gas sensors and their uses.pptxelectrochemical gas sensors and their uses.pptx
electrochemical gas sensors and their uses.pptx
 
Anemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditionsAnemia_ different types_causes_ conditions
Anemia_ different types_causes_ conditions
 
Shuaib Y-basedComprehensive mahmudj.pptx
Shuaib Y-basedComprehensive mahmudj.pptxShuaib Y-basedComprehensive mahmudj.pptx
Shuaib Y-basedComprehensive mahmudj.pptx
 
Structures and textures of metamorphic rocks
Structures and textures of metamorphic rocksStructures and textures of metamorphic rocks
Structures and textures of metamorphic rocks
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
 
GBSN - Microbiology (Lab 2) Compound Microscope
GBSN - Microbiology (Lab 2) Compound MicroscopeGBSN - Microbiology (Lab 2) Compound Microscope
GBSN - Microbiology (Lab 2) Compound Microscope
 
Hemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptxHemoglobin metabolism_pathophysiology.pptx
Hemoglobin metabolism_pathophysiology.pptx
 
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
 
SAMPLING.pptx for analystical chemistry sample techniques
SAMPLING.pptx for analystical chemistry sample techniquesSAMPLING.pptx for analystical chemistry sample techniques
SAMPLING.pptx for analystical chemistry sample techniques
 
Erythropoiesis- Dr.E. Muralinath-C Kalyan
Erythropoiesis- Dr.E. Muralinath-C KalyanErythropoiesis- Dr.E. Muralinath-C Kalyan
Erythropoiesis- Dr.E. Muralinath-C Kalyan
 
INSIGHT Partner Profile: Tampere University
INSIGHT Partner Profile: Tampere UniversityINSIGHT Partner Profile: Tampere University
INSIGHT Partner Profile: Tampere University
 
mixotrophy in cyanobacteria: a dual nutritional strategy
mixotrophy in cyanobacteria: a dual nutritional strategymixotrophy in cyanobacteria: a dual nutritional strategy
mixotrophy in cyanobacteria: a dual nutritional strategy
 
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCINGRNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
 
biotech-regenration of plants, pharmaceutical applications.pptx
biotech-regenration of plants, pharmaceutical applications.pptxbiotech-regenration of plants, pharmaceutical applications.pptx
biotech-regenration of plants, pharmaceutical applications.pptx
 
Aerodynamics. flippatterncn5tm5ttnj6nmnynyppt
Aerodynamics. flippatterncn5tm5ttnj6nmnynypptAerodynamics. flippatterncn5tm5ttnj6nmnynyppt
Aerodynamics. flippatterncn5tm5ttnj6nmnynyppt
 
Mammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also FunctionsMammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also Functions
 
Extensive Pollution of Uranus and Neptune’s Atmospheres by Upsweep of Icy Mat...
Extensive Pollution of Uranus and Neptune’s Atmospheres by Upsweep of Icy Mat...Extensive Pollution of Uranus and Neptune’s Atmospheres by Upsweep of Icy Mat...
Extensive Pollution of Uranus and Neptune’s Atmospheres by Upsweep of Icy Mat...
 

A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary Ergodic Sources

  • 1. A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary Ergodic Sources Joe Suzuki Osaka University October 23, 2010 AWE6 Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 1 / 12
  • 2. Universal Coding for Finite Sources Pn: unknown stationary ergodic   Find Qn . s.t. ∑ xn Qn (xn ) ≤ 1 1 n log Pn(xn) Qn(xn) → 0 for any Xn ∼ Pn with prob. one. Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 2 / 12
  • 3. Universal Coding for Continuous Sources f n: unknown i.i,d. density function with Xi (Ω) ⊆ [0, 1)   Level 0: A0 = {[0, 1/2), [1/2, 1)} consisting of two bins Level 1: A1 = {[0, 1/4), [1/4, 1/2), [1/2, 3/4), [3/4, 1)} of 4 bins . . . . . . Level i: Ai = {[0, 1/2i ), [1/2i , 2/2i ), · · · , [(2i − 1)/2i , 1)} of 2i+1 bins . . . . . . Find Qi for each i to obtain gn (xn ) := ∞∑ i=0 ωi Qi (xn) λi (xn) 1 n log f n(xn) gn(xn) → 0 for any Xn ∼ f n with prob. one. B. Ryabko. IEEE Trans. on Information Theory, VOL. 55, NO. 9, 2009. Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 3 / 12
  • 4. What if no density function exists ? For example, if ∫ ∞ 0 h(x)dx = 1 FX (x) =    0 x < −1, 1 2 , −1 ≤ x < 0∫ x 0 1 2 h(t)dt, 0 ≤ x no fX exists s.t. FX (x) = ∫ x −∞ fX (t)dt.   Random variable X in (Ω, F, µ) Any measurable function X : Ω → R w.r.t. F: D ∈ B =⇒ {ω ∈ Ω|X(ω) ∈ D} ∈ F B: the Borel set of R Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 4 / 12
  • 5. The Radon-Nykodim Theorem µ is absolutely continuous w.r.t. ν (µ << ν) . . . ν(A) = 0 =⇒ µ(A) = 0 Radon-Nykodim derivative dµ dν . . µ << ν =⇒ ∃g s.t. µ(A) = ∫ A g(ω)dν(ω) Finite Sources with prob. P, Q =⇒ dµ dν (xn ) = P(xn) Q(xn) Continuous Sources with Density Functions f , g =⇒ dµ dν (xn ) = f (xn) g(xn) ∃fX = dF dx of FX (x) = µ(X(ω) ≤ x) ⇐⇒ µ << λ λ: the Lebesgue measure on R Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 5 / 12
  • 6. Our Goal µn: unknown stationary ergodic Find νn . . s.t. νn (Xn (Ω)) ≤ 1 1 n log dµn dνn (xn ) → 0 for any Xn ∼ µn with prob. one.   Such a generalization contains as special cases finite sources continuous sources with density functions Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 6 / 12
  • 7. Ryabko’s Measure: Construction {Ai }∞ i=0: sequence of finite sets Ai (Ai+1: a refinment of Ai ) si : R → Ai : the projection to Ai   Qn i (a1, · · · , an) , a1, · · · , an ∈ Ai (via finite universal coding) gn i (x1, · · · , xn) := Qn i (si (x1), · · · , si (xn) λn i (si (x1), · · · , si (xn)) , x1, · · · , xn ∈ R λn i (a1, · · · , an): The Lebesgue measure of (a1, · · · , an) ∈ An i {ωi }∞ i=0: ∞∑ i=0 ωi = 1, ωi > 0 gn (x1, · · · , xn) := ∞∑ i=0 ωi gn i (x1, · · · , xn) Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 7 / 12
  • 8. Ryabko’s Measure: Universality si (Xn) ∼ Pn i f n i (x1, · · · , xn) := Pn i (si (x1), · · · , si (xn)) λn i (si (x1), · · · , si (xn)) Differential entropy . . h(f ∞ ) := lim n→∞ − 1 n ∫ f n (xn ) log f n (xn ) Ryabko, 2009 If h(f ∞ i ) = h(f ∞) as i → ∞, then for any stationary ergodic f ∞, with prob. one, 1 n log f n(x1, · · · , xn) gn(x1, · · · , xn) → 0 Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 8 / 12
  • 9. Proposed Measure: Construction {Xn}∞ n=1 ∼ µ∞   ηn: µn << ηn (ηn = λn =⇒ Ryabko)   For (D1, · · · , Dn) ∈ Bn, νn i (D1, · · · , Dn) := ∑ a1,··· ,an∈Ai ηn(a1 ∩ D1, · · · , an ∩ Dn) ηn(a1, · · · , an) Qn i (a1, · · · , an) .   {ωi }∞ i=0: ∞∑ i=0 ωi = 1, ωi > 0 νn (D1, · · · , Dn) := ∞∑ i=0 ωi νn i (D1, · · · , Dn) Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 9 / 12
  • 10. Proposed Measure: Property si (Xn) ∼ Pn i µn i (D1, · · · , Dn) := ∑ a1,··· ,an∈Ai ηn(a1 ∩ D1, · · · , an ∩ Dn) ηn(a1, · · · , an) Pn i (a1, · · · , an) . Kullback-Leibler Information . . D(µn ||ηn ) := ∫ dµn log dµn dηn Theorem If D(µ∞ i ||η∞) = D(µ∞||η∞) as i → ∞, then for any stationary ergodic µ∞, with prob. one, 1 n log dµn dνn (x1, · · · , xn) → 0 Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 10 / 12
  • 11. Examples ex. 1 Ω := [0, 1), η = λ A0 := {[0, 1/2), [1/2, 1)} A1 := {[0, 1/4), [1/4, 1/2), [1/2, 3/4), [3/4, 1)} · · ·   ex. 2. Ω := N = {1, 2, · · · }, η(j) = 1 j − 1 j + 1 , j ∈ N A0 := {{1}, N − {1}} A1 := {{1}, {2}, N − {1, 2}} · · · Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 11 / 12
  • 12. Conclusion Ryabko’s Histogram Weighing and its Extension . . The generalization was succeeded. Many applications. Direction: The MDL/Bayesian for Continuous Sources . Which is better between νn 1 and νn 2 given observation xn ? =⇒ evaluate dνn 1 dνn 2 (xn ). Joe Suzuki (Osaka University) A Generalization of Nonparametric Estimation and On-Line Prediction for Stationary ErgodOctober 23, 2010 AWE6 12 / 12