Supplementary Material for “Bobrovsky-Zakai Bound for
Filtering, Prediction and Smoothing of Nonlinear Dynamic
Systems”
Carsten Fritsche, Umut Orguner
Division of Automatic Control
E-mail: carsten@isy.liu.se, umut@metu.edu.tr
1st June 2018
Report no.: LiTH-ISY-R-3105
Address:
Department of Electrical Engineering Linköpings universitet
SE-581 83 Linköping, Sweden
WWW: http://www.control.isy.liu.se
AUTOMATIC CONTROL REGLERTEKNIK LINKÖPINGS UNIVERSITET
Technical reports from the Automatic Control group in Linköping are available from http://www.control.isy.liu.se/publications.
theorems that could not be included into the paper due to space limitations. The notation is adapted from the paper.
Supplementary Material for “Bobrovsky-Zakai Bound
for Filtering, Prediction and Smoothing of
Discrete-Time Nonlinear Dynamic Systems”
Carsten Fritsche and Umut Orguner
††
Department of Electrical & Electronics Engineering, Middle East Technical University, 06800, Ankara, Turkey
1
Recursive Computation of Filtering Bound
Lemma 1. The following identities hold (0 < ` < k):
L(Yk; Xk+ hi, Xk) = M0(x1; x0+ h (i) 0 , x0), (1a) L(Yk; Xk+ hnx`+i, Xk) = K`(x`+1, y`; x`+ h (i) ` , x`; x`−1), (1b) L(Yk; Xk+ hnxk+i, Xk) = Lk(yk; xk+ h (i) k , xk; xk−1). (1c)
Proof. We can simplify each ratio of joint densities as follows: L(Yk; Xk+ hi, Xk) = p(Yk, Xk+ hi) p(Yk, Xk) = p(y1|x1) Qk j=2p(yj|xj)p(xj|xj−1) p(y1|x1)Qkj=2p(yj|xj)p(xj|xj−1) p(x1|x0+ h (i) 0 )p(x0+ h (i) 0 ) p(x1|x0)p(x0) = p(x1|x0+ h (i) 0 )p(x0+ h (i) 0 ) p(x1|x0)p(x0) , M0(x1; x0+ h (i) 0 , x0), (2a) L(Yk; Xk+ hnx`+i, Xk) = p(Yk, Xk+ hnx`+i) p(Yk, Xk) = p(y`+1|x`+1) Qk j=`+2p(yj|xj)p(xj|xj−1) p(y`+1|x`+1)Q k j=`+2p(yj|xj)p(xj|xj−1) ×p(x`+1|x`+ h (i) ` )p(y`|x`+ h (i) ` )p(x`+ h (i) ` |x`−1) p(x`+1|x`)p(y`|x`)p(x`|x`−1) ×p(x0) Q`−1 j=1p(yj|xj)p(xj|xj−1) p(x0)Q `−1 j=1p(yj|xj)p(xj|xj−1) = p(x`+1|x`+ h (i) ` )p(y`|x`+ h (i) ` )p(x`+ h (i) ` |x`−1) p(x`+1|x`)p(y`|x`)p(x`|x`−1) , K`(x`+1, y`; x`+ h(i)` , x`; x`−1), (2b) L(Yk; Xk+ hnxk+i, Xk) = p(Yk, Xk+ hnxk+i) p(Yk, Xk) = p(yk|xk+ h (i) k )p(xk+ h (i) k |xk−1) p(yk|xk)p(xk|xk−1) p(x0)Q k−1 j=1p(yj|xj)p(xj|xj−1) p(x0)Q k−1 j=1p(yj|xj)p(xj|xj−1) = p(yk|xk+ h (i) k )p(xk+ h (i) k |xk−1) p(yk|xk)p(xk|xk−1) , Lk(yk; xk+ h (i) k , xk; xk−1). (2c)
Lemma 2. For ξ ≤ k − 2 it holds that
Jk|k(ξ, k) = 0. (3)
Proof. We make use of the fact that due to the Markov property, the product terms inside the expectation in
Jk|k(ξ, k) become independent. In order to see this, let ξ = k − 2 and ξ > 0. Then, the (i, j)-th element of the matrix Jk|k(k − 2, k) can be written as
h
Jk|k(k − 2, k)i
i,j= EL(Yk; Xk+ hnx(k−2)+i, Xk)L(Yk; Xk+ hnxk+j, Xk) − 1 = EnKk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Lk(yk; xk+ h (j) k , xk; xk−1) o − 1. (4) With the tower property of conditional expectations, the above expectation may be rewritten as
E n Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Lk(yk; xk+ h (j) k , xk; xk−1) o = Exk−1 n Eyk−2,xk−2,xk−3|xk−1 n Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3) o × Eyk,xk|xk−1 n Lk(yk; xk+ h (j) k , xk; xk−1) o o . (5) Since Eyk−2,xk−2,xk−3|xk−1 n Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3) o = Z p(x k−1|xk−2+ h (i) k−2) p(xk−1|xk−2) p(yk−2|xk−2+ h (i) k−2)p(xk−2+ h (i) k−2|xk−3) p(yk−2|xk−2)p(xk−2|xk−3) × p(yk−2, xk−2, xk−3|xk−1) dyk−2dxk−2dxk−3 = Z p(x k−1|xk−2+ h (i) k−2) p(xk−1|xk−2) p(yk−2|xk−2+ h (i) k−2)p(xk−2+ h (i) k−2|xk−3) p(yk−2|xk−2)p(xk−2|xk−3) ×p(xk−1|xk−2)p(yk−2|xk−2)p(xk−2|xk−3)p(xk−3) p(xk−1) dyk−2dxk−2dxk−3 = Z p(x k−1|xk−2+ h (i) k−2)p(yk−2|xk−2+ h (i) k−2)p(xk−2+ h (i) k−2|xk−3)p(xk−3) p(xk−1) dyk−2dxk−2dxk−3 = 1 p(xk−1) Z p(xk−1|xk−2+ h (i) k−2) Z p(yk−2|xk−2+ h (i) k−2)dyk−2 p(xk−2+ h (i) k−2, xk−3) dxk−2dxk−3 = 1 p(xk−1) Z p(xk−1, xk−2+ h (i) k−2) dxk−2 = 1 (6a) and Eyk,xk|xk−1 n Lk(yk; xk+ h (j) k , xk; xk−1) o = Z p(y k|xk+ h (j) k )p(xk+ h (j) k |xk−1) p(yk|xk)p(xk|xk−1) p(yk, xk|xk−1) dykdxk = Z p(y k|xk+ h (j) k )p(xk+ h (j) k |xk−1) p(yk|xk)p(xk|xk−1) p(yk|xk)p(xk|xk−1) dykdxk = Z Z p(yk|xk+ h (j) k ) dyk p(xk+ h (j) k |xk−1)dxk = 1, (6b) we obtain h Jk|k(k − 2, k)i i,j = 0. (7)
This can be generalized for 0 < ξ < k − 2 as follows: h Jk|k(ξ, k)i i,j= E {L(Yk ; Xk+ hnxξ+i, Xk)L(Yk; Xk+ hnxk+j, Xk)} − 1 = EnKξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Lk(yk; xk+ h (j) k , xk; xk−1) o − 1 = Exξ+1,yξ,xξ,xξ−1 n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1) o Eyk,xk,xk−1 n Lk(yk; xk+ h (j) k , xk; xk−1) o − 1. (8)
Now, since Exξ+1,yξ,xξ,xξ−1 n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1) o = Z p(xξ+1|xξ+ h(i) ξ ) p(xξ+1|xξ) p(yξ|xξ+ h (i) ξ )p(xξ+ h (i) ξ |xξ−1) p(yξ|xξ)p(xξ|xξ−1) p(xξ+1, yξ, xξ, xξ−1) dxξ+1dyξdxξdxξ−1 = Z p(xξ+1|xξ+ h (i) ξ )p(yξ|xξ+ h (i) ξ )p(xξ+ h (i) ξ |xξ−1)p(xξ−1) dxξ+1dyξdxξdxξ−1 = Z Z p(xξ+1|xξ+ h (i) ξ ) dxξ+1 Z p(yξ|xξ+ h (i) ξ ) dyξ p(xξ+ h (i) ξ , xξ−1) dxξdxξ−1 = Z p(xξ+ h (i) ξ , xξ−1) dxξdxξ−1 = 1 (9a) and Eyk,xk,xk−1 n Lk(yk; xk+ h (j) k , xk; xk−1) o = Z p(y k|xk+ h (j) k )p(xk+ h (j) k |xk−1) p(yk|xk)p(xk|xk−1) p(yk, xk, xk−1) dykdxkdxk−1 = Z p(yk|xk+ h (j) k )p(xk+ h (j) k |xk−1)p(xk−1) dykdxkdxk−1 = Z Z p(yk|xk+ h (j) k ) dyk p(xk+ h (j) k , xk−1)dxkdxk−1 = 1, (9b) holds, we arrive at h Jk|k(ξ, k)i i,j = 0. (10)
Finally, for ξ = 0 we have h Jk|k(0, k)i i,j= E {L(Yk ; Xk+ hi, Xk)L(Yk; Xk+ hnxk+j, Xk)} − 1 = EnM0(x1; x0+ h (i) 0 , x0)Lk(yk; xk+ h (j) k , xk; xk−1) o − 1 = Ex1 n Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o Ey2,x2|x1 n L2(y2; x2+ h (j) 2 , x2; x1) oo − 1, k = 2, Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o Eyk,xk,xk−1 n Lk(yk; xk+ h (j) k , xk; xk−1) o − 1, k > 2. (11) Since Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o = Z p(x 1|x0+ h (i) 0 )p(x0+ h (i) 0 ) p(x1|x0)p(x0) p(x0|x1) dx0 = Z p(x 1, x0+ h (i) 0 ) p(x1|x0)p(x0) p(x1|x0)p(x0) p(x1) dx0 = 1, (12a) Ey2,x2|x1 n L2(y2; x2+ h (j) 2 , x2; x1) o = 1, (12b) Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o = Z p(x 1|x0+ h (i) 0 )p(x0+ h (i) 0 ) p(x1|x0)p(x0) p(x1|x0)p(x0) dx1dx0 = 1, (12c) Eyk,xk,xk−1 n Lk(yk; xk+ h (j) k , xk; xk−1) o = 1 (12d) holds, we arrive at h Jk|k(0, k)i i,j = 0. (13)
Lemma 3. For ξ ≤ k − 3 it holds that
Jk|k(ξ, k − 1) = 0. (14)
Proof. Let ξ = k − 3 and ξ > 0. Then, we obtain
h
Jk|k(k − 3, k − 1)i
i,j= EL(Yk; Xk+ hnx(k−3)+i, Xk)L(Yk; Xk+ hnx(k−1)+j, Xk) − 1 = EnKk−3(xk−2, yk−3; xk−3+ h (i) k−3, xk−3; xk−4)Kk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2) o − 1 = Exk−2 n Eyk−3,xk−3,xk−4|xk−2 n Kk−3(xk−2, yk−3; xk−3+ h (i) k−3, xk−3; xk−4) o × Exk,yk−1,xk−1|xk−2 n Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o o − 1 = 0, (15)
where the last equality follows from Eyk−3,xk−3,xk−4|xk−2 n Kk−3(xk−2, yk−3; xk−3+ h (i) k−3, xk−3; xk−4) o = Z p(x k−2|xk−3+ h (i) k−3) p(xk−2|xk−3) p(yk−3|xk−3+ h (i) k−3)p(xk−3+ h (i) k−3|xk−4) p(yk−3|xk−3)p(xk−3|xk−4) × p(yk−3, xk−3, xk−4|xk−2) dyk−3dxk−3dxk−4 = Z p(x k−2|xk−3+ h (i) k−3) p(xk−2|xk−3) p(yk−3|xk−3+ h (i) k−3)p(xk−3+ h (i) k−3|xk−4) p(yk−3|xk−3)p(xk−3|xk−4) ×p(xk−2|xk−3)p(yk−3|xk−3)p(xk−3|xk−4)p(xk−4) p(xk−2) dyk−3dxk−3dxk−4 = Z p(x k−2|xk−3+ h (i) k−3)p(yk−3|xk−3+ h (i) k−3)p(xk−3+ h (i) k−3|xk−4)p(xk−4) p(xk−2) dyk−3dxk−3dxk−4 = 1 p(xk−2) Z p(xk−2|xk−3+ h (i) k−3) Z p(yk−3|xk−3+ h (i) k−3)dyk−3 p(xk−3+ h (i) k−3, xk−4) dxk−3dxk−4 = 1 p(xk−2) Z p(xk−2, xk−3+ h (i) k−3) dxk−3 = 1 (16a) and Exk,yk−1,xk−1|xk−2 n Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o = Z p(x k|xk−1+ h (j) k−1) p(xk|xk−1) p(yk−1|xk−1+ h (j) k−1)p(xk−1+ h (j) k−1|xk−2) p(yk−1|xk−1)p(xk−1|xk−2) p(xk, yk−1, xk−1|xk−2) dxkdyk−1dxk−1 = Z p(xk|xk−1+ h (j) k−1) Z p(yk−1|xk−1+ h (j) k−1)dyk−1 p(xk−1+ h (j) k−1|xk−2) dxkdxk−1 = Z Z p(xk|xk−1+ hk−1(j) ) dxk p(xk−1+ h(j)k−1|xk−2) dxk−1 = 1. (16b)
This can be generalized for 0 < ξ < k − 3 as follows: h Jk|k(ξ, k − 1)i i,j= EL(Yk ; Xk+ hnxξ+i, Xk)L(Yk; Xk+ hnx(k−1)+j, Xk) − 1 = EnKξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1 = Exξ+1,yξ,xξ,xξ−1 n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1) o × Exk,yk−1,xk−1,xk−2 n Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1 = 0, (17)
where the last equality follows from (9a) and Exk,yk−1,xk−1,xk−2 n Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o = Z p(x k|xk−1+ h (j) k−1) p(xk|xk−1) p(yk−1|xk−1+ h (j) k−1)p(xk−1+ h (j) k−1|xk−2) p(yk−1|xk−1)p(xk−1|xk−2) × p(xk, yk−1, xk−1, xk−2) dxkdyk−1dxk−1dxk−2 = Z p(xk|xk−1+ h (j) k−1) Z p(yk−1|xk−1+ h (j) k−1)dyk−1 p(xk−1+ h (j) k−1|xk−2)p(xk−2) dxkdxk−1dxk−2 = Z Z p(xk|xk−1+ h (j) k−1) dxk p(xk−1+ h (j) k−1, xk−2) dxk−1dxk−2 = 1. (18)
Finally, for ξ = 0 we have h Jk|k(0, k − 1)i i,j= EL(Yk ; Xk+ hi, Xk)L(Yk; Xk+ hnx(k−1)+j, Xk) − 1 = EnM0(x1; x0+ h (i) 0 , x0)Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1 = Ex1 n Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o Ex3,y2,x2|x1 n K2(x3, y2; x2+ h (j) 2 , x2; x1) oo − 1, k = 3, Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o Exk,yk−1,xk−1,xk−2 n Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1, k > 3. (19) Since Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o = 1, (20a) Ex3,y2,x2|x1 n K2(x3, y2; x2+ h (j) 2 , x2; x1) o = 1, (20b) Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o = 1, (20c) Exk,yk−1,xk−1,xk−2 n Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o = 1 (20d) holds, we arrive at h Jk|k(0, k − 1)i i,j = 0. (21)
This concludes the proof of Lemma 3.
Corollary 1. For ξ ≤ k − 3 it holds that
Jk−1|k−1(ξ, k − 1) = 0. (22)
Proof. Follows from Lemma 2.
Lemma 4. The following identity holds
Jk|k(k − 2, k − 1) = Jk−1|k−1(k − 2, k − 1). (23)
Proof. For k > 2 it holds
h Jk|k(k − 2, k − 1)i i,j= EL(Yk ; Xk+ hnx(k−2)+i, Xk)L(Yk; Xk+ hnx(k−1)+j, Xk) − 1 = EKk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) − 1 = EnKk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Lk−1(yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1, (24)
where the last equality follows from E n Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o = Z Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3) p(xk|xk−1+ h (j) k−1) p(xk|xk−1) p(yk−1|xk−1+ h (j) k−1)p(xk−1+ h (j) k−1|xk−2) p(yk−1|xk−1)p(xk−1|xk−2) × p(xk, xk−1, yk−1, yk−2, xk−2, xk−3)dxkdxk−1dyk−1dyk−2dxk−2dxk−3 = Z Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3) Z p(xk|xk−1+ h (j) k−1)dxk p(y k−1|xk−1+ h (j) k−1) p(yk−1|xk−1) ×p(xk−1+ h (j) k−1|xk−2) p(xk−1|xk−2) p(xk−1, yk−1, yk−2, xk−2, xk−3)dxk−1dyk−1dyk−2dxk−2dxk−3 = Z Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3) p(yk−1|xk−1+ h (j) k−1)p(xk−1+ h (j) k−1|xk−2) p(yk−1|xk−1)p(xk−1|xk−2) × p(xk−1, yk−1, yk−2, xk−2, xk−3)dxk−1dyk−1dyk−2dxk−2dxk−3 = EnKk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Lk−1(yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o . (25) Now, since h Jk−1|k−1(k − 2, k − 1)i i,j= EL(Yk−1 ; Xk−1+ hnx(k−2)+i, Xk−1)L(Yk−1; Xk−1+ hnx(k−1)+j, Xk−1) − 1 = EKk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Lk−1(yk−1; xk−1+ h (j) k−1, xk−1; xk−2) − 1 (26) holds, we have proved the first part. In case k = 2, we have
h
J2|2(0, 1)i
i,j= E {L(Y2; X2+ hi, X2)L(Y2; X2+ hnx+j, X2)} − 1 = EM0(x1; x0+ h (i) 0 , x0)K1(x2, y1; x1+ h (j) 1 , x1; x0) − 1 = Z M0(x1; x0+ h (i) 0 , x0) p(x2|x1+ h (j) 1 ) p(x2|x1) p(y1|x1+ h (j) 1 )p(x1+ h (j) 1 |x0) p(y1|x1)p(x1|x0) × p(x2, x1, y1, x0)dx2dx1dy1dx0 = Z M0(x1; x0+ h (i) 0 , x0) Z p(x2|x1+ h (j) 1 ) dx2 p(y1|x1+ h (j) 1 )p(x1+ h (j) 1 |x0) p(y1|x1)p(x1|x0) × p(x1, y1, x0)dx1dy1dx0 = EM0(x1; x0+ h (i) 0 , x0)L1(y1; x1+ h (j) 1 , x1; x0) − 1. (27)
But this is equal to h J1|1(0, 1)i i,j = E {L(Y1 ; X1+ hi, X1)L(Y1; X1+ hnx+j, X1)} − 1 = EM0(x1; x0+ h (i) 0 , x0)L1(y1; x1+ h (j) 1 , x1; x0) − 1. (28)
This concludes the proof of Lemma 4.
Lemma 5. For ξ, η ≤ k − 2 it holds that
Jk|k(ξ, η) = Jk−1|k−1(ξ, η). (29)
Proof. For 0 < ξ, η ≤ k − 2 it follows
h
Jk|k(ξ, η)i
i,j= EYk,Xk
{L(Yk; Xk+ hnxξ+i, Xk)L(Yk; Xk+ hnxη+j, Xk)} − 1 = EYk,Xk n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1. (30) The expression inside the expectation depends neither on yk nor xk. Hence, these variables can be integrated out yielding h Jk|k(ξ, η)i i,j= EYk−1,Xk−1 n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1 = hJk−1|k−1(ξ, η)i i,j (31)
For ξ = η = 0 (and k ≥ 2) it follows h
Jk|k(0, 0)i
i,j = EYk,Xk{L(Yk; Xk+ hi, Xk)L(Yk; Xk+ hj, Xk)} − 1 = Ex1,x0 n M0(x1; x0+ h (i) 0 , x0)M0(x1; x0+ h (j) 0 , x0) o − 1. (32) This is equal to h Jk−1|k−1(0, 0)i i,j= EYk−1,Xk−1{L(Yk−1; Xk−1+ hi , Xk−1)L(Yk−1; Xk−1+ hj, Xk−1)} − 1 = Ex1,x0 n M0(x1; x0+ h (i) 0 , x0)M0(x1; x0+ h (j) 0 , x0) o − 1. (33)
Similarly, for ξ = 0 and 0 < η ≤ k − 2 we obtain h Jk|k(0, η)i i,j = EYk,Xk {L(Yk; Xk+ hi, Xk)L(Yk; Xk+ hnxη+j, Xk)} − 1 = EYk,Xk n M0(x1; x0+ h (i) 0 , x0)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1. (34)
The expression inside the expectation depends neither on yk nor xk. Hence, we can write h Jk|k(0, η)i i,j = EYk−1,Xk−1 n M0(x1; x0+ h (i) 0 , x0)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1 = hJk−1|k−1(0, η)i i,j . (35)
Essentially the same reasoning can be used to show that h Jk|k(ξ, 0)i i,j= h Jk−1|k−1(ξ, 0)i i,j, (36)
where 0 < ξ ≤ k − 2. This concludes the proof of Lemma 5.
Theorem 1. The MSE matrix for the filtering problem is bounded below by
Exk,Yk(xk−xbk(Yk))(·)
T H(k, k) J
k|k −1
HT(k, k), (37)
where the information matrix Jk|k can be computed recursively as
Jk|k= Jk|k(k, k) − Jk|k(k, k − 1) h Jk|k(k − 1, k − 1) − Jk−1|k−1(k − 1, k − 1) + Jk−1|k−1 i−1 Jk|k(k − 1, k), (38)
with initialization J0|0 = J0|0(0, 0). The (i, j)-th elements of the matrices Jk|k(ξ, η) are given by
h Jk|k(k, k)i i,j= E n Lk(yk; xk+ h (i) k , xk; xk−1)Lk(yk; xk+ h (j) k , xk; xk−1) o − 1, (39a) h Jk|k(k, k − 1)i i,j = hJk|k(k − 1, k)i j,i = E n L1(y1; x1+ h (i) 1 , x1; x0)M0(x1; x0+ h (j) 0 , x0) o − 1, k = 1, E n Lk(yk; xk+ h (i) k , xk; xk−1)Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1, k > 1, (39b) h Jk|k(k − 1, k − 1)i i,j = E n M0(x1; x0+ h (i) 0 , x0)M0(x1; x0+ h (j) 0 , x0) o − 1, k = 1, E n Kk−1(xk, yk−1; xk−1+ h(i)k−1, xk−1; xk−2)Kk−1(xk, yk−1; xk−1+ h(j)k−1, xk−1; xk−2) o − 1, k > 1. (39c)
Proof. We partition the information matrix Jk−1|k−1 at time instance k − 1 as follows:
Jk−1|k−1= A k−1|k−1 Bk−1|k−1 BT k−1|k−1 J k−1|k−1(k − 1, k − 1) , (40)
where Ak−1|k−1 = Jk−1|k−1(0, 0) · · · Jk−1|k−1(0, k − 2) .. . . .. ... Jk−1|k−1(k − 2, 0) · · · Jk−1|k−1(k − 2, k − 2) , (41a) Bk−1|k−1= Jk−1|k−1(0, k − 1) .. . Jk−1|k−1(k − 3, k − 1) Jk−1|k−1(k − 2, k − 1) Corollary 1 = 0 .. . 0 Jk−1|k−1(k − 2, k − 1) . (41b)
The information sub-matrix Jk−1|k−1 for estimating xk−1 is the inverse of the (nx× nx) lower-right sub-block ofJk−1|k−1−1
and can be obtained from block matrix inversion as follows:
Jk−1|k−1 = Jk−1|k−1(k − 1, k − 1) − BTk−1|k−1Ak−1|k−1 −1
Bk−1|k−1. (42)
Similarly, the information matrix Jk|kat time k can be partitioned according to
Jk|k= Ak|k Bk|k Ck|k BTk|k Jk|k(k − 1, k − 1) Jk|k(k − 1, k) CT k|k J k|k(k, k − 1) Jk|k(k, k) , (43) where Ak|k= Jk|k(0, 0) · · · Jk|k(0, k − 2) .. . . .. ... Jk|k(k − 2, 0) · · · Jk|k(k − 2, k − 2) Lemma 5 = Ak−1|k−1, (44a) Bk|k= Jk|k(0, k − 1) .. . Jk|k(k − 3, k − 1) Jk|k(k − 2, k − 1) Lemma 3,4 = Bk−1|k−1 (44b) and Ck|k= Jk|k(0, k) .. . Jk|k(k − 2, k) Lemma 2 = 0 .. . 0 . (44c)
Hence, the information matrix Jk|kcan be reduced to
Jk|k= A k−1|k−1 Bk−1|k−1 BT k−1|k−1 J k|k(k − 1, k − 1) 0 Jk|k(k − 1, k) 0 Jk|k(k, k − 1) Jk|k(k, k) . (45)
The (nx× nx) information sub-matrix Jk|kis again obtained from block-matrix inversion, yielding the recursion
Jk|k= Jk|k(k, k) − 0 Jk|k(k − 1, k) T" ? ? ? hJk|k(k − 1, k − 1) − BTk−1|k−1Ak−1|k−1 −1 Bk−1|k−1 i−1 # × 0 Jk|k(k − 1, k) = Jk|k(k, k) − Jk|k(k, k − 1)hJk|k(k − 1, k − 1) − Jk−1|k−1(k − 1, k − 1) + Jk−1|k−1 i−1 Jk|k(k − 1, k), (46)
where the last equality follows by using (42). The matrix elements Jk|k(η, ξ) constituting the above recursion can be obtained by making use of the results provided in Lemma 1. This yields
h Jk|k(k, k)i i,j= h Jk|ki nxk+i,nxk+j
= E {L(Yk; Xk+ hnxk+i, Xk)L(Yk; Xk+ hnxk+j, Xk)} − 1 = EnLk(yk; xk+ h (i) k , xk; xk−1)Lk(yk; xk+ h (j) k , xk; xk−1) o − 1 = E ( p(yk|xk+ h (i) k )p(yk|xk+ h (j) k )p(xk+ h (i) k |xk−1)p(xk+ h (j) k |xk−1) p2(y k|xk)p2(xk|xk−1) ) − 1, (47a) h Jk|k(k, k − 1)i i,j =hJk|ki nxk+i,nx(k−1)+j =hJk|k(k − 1, k)i j,i
= EL(Yk; Xk+ hnxk+i, Xk)L(Yk; Xk+ hnx(k−1)+j, Xk) − 1 = E n L1(y1; x1+ h (i) 1 , x1; x0)M0(x1; x0+ h (j) 0 , x0) o − 1, k = 1, E n Lk(yk; xk+ h (i) k , xk; xk−1)Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1, k > 1, = E p(x1+h(i)1 |x0)p(x1|x0+h(j)0 )p(x0+h(j)0 ) p2(x1|x0)p(x0) − 1, k = 1, E p(xk+h(i)k |xk−1)p(xk|xk−1+h(j)k−1)p(xk−1+h(j)k−1|xk−2) p2(xk|xk−1)p(xk−1|xk−2) − 1, k > 1, (47b) h Jk|k(k − 1, k − 1)i i,j =hJ(k)i nx(k−1)+i,nx(k−1)+j
= EL(Yk; Xk+ hnx(k−1)+i, Xk)L(Yk; Xk+ hnx(k−1)+j, Xk) − 1 = E n M0(x1; x0+ h (i) 0 , x0)M0(x1; x0+ h (j) 0 , x0) o − 1, k = 1, E n Kk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2)Kk−1(xk, yk−1; xk−1+ h (j) k−1, xk−1; xk−2) o − 1, k > 1, = E p(x1|x0+h(i)0 )p(x1|x0+h(j)0 )p(x0+h(i)0 )p(x0+h(j)0 ) p2(x 1|x0)p2(x0) − 1, k = 1, E
p(xk|xk−1+h(i)k−1)p(xk|xk−1+h(j)k−1)p(yk−1|xk−1+h(i)k−1)p(yk−1|xk−1+h(j)k−1) p2(xk|xk−1)p2(yk−1|xk−1) ×p(xk−1+h (i) k−1|xk−2)p(xk−1+h (j) k−1|xk−2) p2(xk−1|xk−2) − 1, k > 1. (47c)
This concludes the proof of Theorem 1.
2
Recursive Computation of Prediction Bound
Theorem 2. The MSE matrix for the one-step ahead prediction problem is bounded below by
Exk+1,Yk(xk+1−bxk+1(Yk))(·)
T H(k + 1, k + 1) J
k+1|k −1
HT(k + 1, k + 1), (48)
where the prediction information sub-matrix Jk+1|k can be computed from the recursion
Jk+1|k= Jk+1|k(k + 1, k + 1) − Jk+1|k(k + 1, k) h
Jk+1|k(k, k) − Jk|k(k, k) + Jk|k i−1
Jk+1|k(k, k + 1) (49)
with initialization J0|0. The (i, j)-th element of the matrix Jk+1|k(k + 1, k + 1) is given by
h Jk+1|k(k + 1, k + 1)i i,j = E ( p(xk+1+ h (i) k+1|xk)p(xk+1+ h (j) k+1|xk) p2(x k+1|xk) ) − 1. (50)
Proof. The one-step ahead prediction information matrix Jk+1|k is partitioned into blocks Jk+1|k(ξ, η), ξ, η = 0, . . . , k + 1 each of size (nx× nx) as follows
Jk+1|k ∆= Jk+1|k(0, 0) Jk+1|k(0, 1) · · · Jk+1|k(0, k) Jk+1|k(0, k + 1) Jk+1|k(1, 0) Jk+1|k(1, 1) · · · Jk+1|k(1, k) Jk+1|k(1, k + 1) .. . ... . .. ... ... Jk+1|k(k, 0) Jk+1|k(k, 1) · · · Jk+1|k(k, k) Jk+1|k(k, k + 1) Jk+1|k(k + 1, 0) Jk+1|k(k + 1, 1) · · · Jk+1|k(k + 1, k) Jk+1|k(k + 1, k + 1) , (51)
where each block is given by h Jk+1|k(ξ, η)i i,j = hJk+1|ki nxξ+i,nxη+j
= EYk,Xk+1{L(Yk, Xk+1+ hnxξ+i, Xk+1)L(Yk, Xk+1+ hnxη+j, Xk+1)} − 1. (52) The idea is now, similarly to the proof for the filtering bound, to identify blocks in the matrix Jk+1|kthat are identical to the blocks in the matrix Jk|k, i.e. they do not change over time, such that a recursive computation of the prediction information sub-matrix Jk+1|kin terms of the filtering information sub-matrix Jk|kis possible. In order to prove the above stated recursion, the following lemmas are required:
Lemma 6. The following identities hold (0 < ` < k + 1):
L(Yk; Xk+1+ hi, Xk+1) = M0(x1; x0+ h (i) 0 , x0), (53a) L(Yk; Xk+1+ hnx`+i, Xk+1) = K`(x`+1, y`; x`+ h (i) ` , x`; x`−1), (53b) L(Yk; Xk+1+ hnx(k+1)+i, Xk+1) = Nk+1(xk+1+ h (i) k , xk+1; xk). (53c)
Proof. We can simplify each ratio of joint densities as follows:
L(Yk; Xk+1+ hi, Xk+1) = p(Yk, Xk+1+ hi) p(Yk, Xk+1) = p(xk+1|xk)p(y1|x1) Qk j=2p(yj|xj)p(xj|xj−1) p(xk+1|xk)p(y1|x1)Q k j=2p(yj|xj)p(xj|xj−1) p(x1|x0+ h (i) 0 )p(x0+ h (i) 0 ) p(x1|x0)p(x0) = p(x1|x0+ h (i) 0 )p(x0+ h (i) 0 ) p(x1|x0)p(x0) = M0(x1; x0+ h (i) 0 , x0), (54a) L(Yk; Xk+1+ hnx`+i, Xk+1) = p(Yk+1, Xk+1+ hnx`+i) p(Yk, Xk+1) = p(xk+1|xk)p(y`+1|x`+1) Qk j=`+2p(yj|xj)p(xj|xj−1) p(xk+1|xk)p(y`+1|x`+1)Q k j=`+2p(yj|xj)p(xj|xj−1) ×p(x`+1|x`+ h (i) ` )p(y`|x`+ h (i) ` )p(x`+ h (i) ` |x`−1) p(x`+1|x`)p(y`|x`)p(x`|x`−1) ×p(x0) Q`−1 j=1p(yj|xj)p(xj|xj−1) p(x0)Q `−1 j=1p(yj|xj)p(xj|xj−1) = p(x`+1|x`+ h (i) ` )p(y`|x`+ h (i) ` )p(x`+ h (i) ` |x`−1) p(x`+1|x`)p(y`|x`)p(x`|x`−1) = K`(x`+1, y`; x`+ h (i) ` , x`; x`−1), (54b) L(Yk; Xk+1+ hnx(k+1)+i, Xk+1) = p(Yk, Xk+1+ hnx(k+1)+i) p(Yk, Xk+1) = p(xk+1+ h (i) k |xk) p(xk+1|xk) p(x0)Qkj=1p(yj|xj)p(xj|xj−1) p(x0)Q k−1 j=1p(yj|xj)p(xj|xj−1) = p(xk+1+ h (i) k |xk) p(xk+1|xk) , Nk+1(xk+1+ h (i) k+1, xk+1; xk). (54c)
This concludes the proof of Lemma 6.
Lemma 7. For ξ ≤ k − 1 it holds that
Proof. Let ξ = k − 1 and ξ > 0. Then, the (i, j)-th element of the matrix Jk+1|k(k − 1, k + 1) can be written as h
Jk+1|k(k − 1, k + 1)i
i,j= EL(Yk; Xk+1+ hnx(k−1)+i, Xk+1)L(Yk; Xk+1+ hnx(k+1)+j, Xk+1) − 1 = EnKk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2)Nk+1(xk+1+ h (j) k+1, xk+1; xk) o − 1. (56) The tower property of conditional expectations gives
E n Kk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2)Nk+1(xk+1+ h (j) k+1, xk+1; xk) o = Exk n Eyk−1,xk−1,xk−2|xk n Kk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2) o × Exk+1|xk n Nk+1(xk+1+ h (j) k+1, xk+1; xk) o o . (57) Since Eyk−1,xk−1,xk−2|xk n Kk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2) o = 1 (58a) and Exk+1|xk n Nk+1(xk+1+ h (j) k+1, xk+1; xk) o = Z p(x k+1+ h (j) k+1|xk) p(xk+1|xk) p(xk+1|xk) dxk+1 = 1, (58b) we obtain h Jk+1|k(k − 1, k + 1)i i,j= 0. (59)
This can be generalized for 0 < ξ < k − 1 as follows: h Jk+1|k(ξ, k + 1)i i,j= EL(Yk ; Xk+1+ hnxξ+i, Xk+1)L(Yk; Xk+1+ hnx(k+1)+j, Xk+1) − 1 = EnKξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Nk+1(xk+1+ h (j) k+1, xk+1; xk) o − 1 = Exξ+1,yξ,xξ,xξ−1 n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1) o Exk+1,xk n Nk+1(xk+1+ h (j) k+1, xk+1; xk) o − 1. (60) Now, since Exξ+1,yξ,xξ,xξ−1 n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1) o = 1 (61a) and Exk+1,xk n Nk+1(xk+1+ h (j) k+1, xk+1; xk) o = Z "Z p(x k+1+ h (j) k+1xk) p(xk+1|xk) p(xk+1|xk) dxk+1 # p(xk) dxk = 1, (61b) holds, we arrive at h Jk+1|k(ξ, k + 1)i i,j = 0. (62)
Finally, for ξ = 0 we have h Jk+1|k(0, k + 1)i i,j= EL(Yk ; Xk+1+ hi, Xk+1)L(Yk; Xk+1+ hnx(k+1)+j, Xk+1) − 1 = EnM0(x1; x0+ h (i) 0 , x0)Nk+1(xk+1+ h (j) k+1, xk+1; xk) o − 1 = Ex1 n Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o Ex2|x1 n N2(x2+ h (j) 2 , x2; x1) oo − 1, k = 1, Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o Exk+1,xk n Nk+1(xk+1+ h (j) k+1, xk+1; xk) o − 1, k > 1. (63)
Since Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o = 1, (64a) Ex2|x1 n N2(x2+ h (j) 2 , x2; x1) o = 1, (64b) Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o = 1, (64c) Exk+1,xk n Nk+1(xk+1+ h (j) k+1, xk+1; xk) o = 1, (64d) holds, we arrive at h Jk+1|k(0, k + 1)i i,j = 0. (65)
This concludes the proof of Lemma 7.
Lemma 8. For ξ ≤ k − 2 it holds that
Jk+1|k(ξ, k) = Jk|k(ξ, k) = 0. (66)
Proof. Let ξ = k − 2 and ξ > 0. Then, we obtain
h Jk+1|k(k − 2, k)i i,j = EL(Yk ; Xk+1+ hnx(k−2)+i, Xk+1)L(Yk; Xk+1+ hnxk+j, Xk+1) − 1 = EnKk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3)Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o − 1 = Exk−1 n Eyk−2,xk−2,xk−3|xk−1 n Kk−2(xk−1, yk−2; xk−2+ h (i) k−2, xk−2; xk−3) o × Exk+1,yk,xk|xk−1 n Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o o − 1 = 0, (67)
where the last equality follows from Eyk−2,xk−2,xk−3|xk−1 n Kk−2(xk−1, yk−2; xk−2+ h(i)k−2, xk−2; xk−3) o = 1, (68a) and Exk+1,yk,xk|xk−1 n Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o = 1. (68b)
This can be generalized for 0 < ξ < k − 2 as follows: h Jk+1|k(ξ, k)i i,j= E {L(Yk ; Xk+1+ hnxξ+i, Xk+1)L(Yk; Xk+1+ hnxk+j, Xk+1)} − 1 = EnKξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o − 1 = Exξ+1,yξ,xξ,xξ−1 n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1) o × Exk+1,yk,xk,xk−1 n Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o − 1 = 0, (69)
where the last equality follows from (61a) and Exk+1,yk,xk,xk−1 n Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o = 1. (70)
Finally, for ξ = 0 we have h Jk+1|k(0, k)i i,j = E {L(Yk ; Xk+1+ hi, Xk+1)L(Yk; Xk+1+ hnxk+j, Xk+1)} − 1 = EnM0(x1; x0+ h (i) 0 , x0)Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o − 1 = Ex1 n Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o Ex3,y2,x2|x1 n K2(x3, y2; x2+ h (j) 2 , x2; x1) oo − 1, k = 2, Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o Exk+1,yk,xk,xk−1 n Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o − 1, k > 2. (71)
Since Ex0|x1 n M0(x1; x0+ h (i) 0 , x0) o = 1, (72a) Ex3,y2,x2|x1 n K2(x3, y2; x2+ h (j) 2 , x2; x1) o = 1, (72b) Ex1,x0 n M0(x1; x0+ h (i) 0 , x0) o = 1, (72c) Exk+1,yk,xk,xk−1 n Kk(xk+1, yk; xk+ h(j)k , xk; xk−1) o = 1 (72d) holds, we arrive at h Jk+1|k(0, k)i i,j = 0. (73)
Now comparing this with the result stated in Lemma 2 concludes the proof.
Lemma 9. The following identity holds
Jk+1|k(k − 1, k) = Jk|k(k − 1, k) (74)
Proof. For k > 1 it holds
h
Jk+1|k(k − 1, k)i
i,j = EL(Yk; Xk+1+ hnx(k−1)+i
, Xk+1)L(Yk; Xk+1+ hnxk+j, Xk+1) − 1 = EKk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2)Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) − 1 = E ( p(xk|xk−1+ h (i) k−1)p(xk−1+ h (i) k−1|xk−2)p(xk+ h (j) k |xk−1) p2(x k|xk−1)p(xk−1|xk−2) ) − 1, (75)
where the last equality follows from integrating out the variables xk+1, yk and yk−1. Similarly, integrating out the variables yk and yk−1 in
h Jk|k(k − 1, k)i i,j= EL(Yk ; Xk+ hnx(k−1)+i, Xk)L(Yk; Xk+ hnxk+j, Xk) − 1 = EKk−1(xk, yk−1; xk−1+ h (i) k−1, xk−1; xk−2)Lk(yk; xk+ h (j) k , xk; xk−1) − 1 = E ( p(xk|xk−1+ h (i) k−1)p(xk−1+ h (i) k−1|xk−2)p(xk+ h (j) k |xk−1) p2(x k|xk−1)p(xk−1|xk−2) ) − 1, (76)
yields the equality. For k = 1 we arrive at h J2|1(0, 1)i i,j = E {L(Y1 ; X2+ hi, X2)L(Y1; X2+ hnx+j, X2)} − 1 = EM0(x1; x0+ h (i) 0 , x0)K1(x2, y1; x1+ h (j) 1 , x1; x0) − 1 = E ( p(x1|x0+ h (i) 0 )p(x0+ h (i) 0 )p(x1+ h (j) 1 |x0) p2(x 1|x0)p(x0) ) − 1, (77)
where the last equality follows from integrating out the variables x2 and y1. Similarly, integrating out the
variable y1 in h J1|1(0, 1)i i,j = E {L(Y1; X1+ hi , X1)L(Y1; X1+ hnx+j, X1)} − 1 = EM0(x1; x0+ h (i) 0 , x0)L1(y1; x1+ h (j) 1 , x1; x0) − 1 = E ( p(x1|x0+ h (i) 0 )p(x0+ h (i) 0 )p(x1+ h (j) 1 |x0) p2(x 1|x0)p(x0) ) − 1 (78)
yields the equality. This concludes the proof of Lemma 9.
Lemma 10. For ξ, η ≤ k − 1 it holds that
Proof. For 0 < ξ, η ≤ k − 1 it follows
h
Jk+1|k(ξ, η)i
i,j = EYk,Xk+1
{L(Yk; Xk+1+ hnxξ+i, Xk+1)L(Yk; Xk+1+ hnxη+j, Xk+1)} − 1 = EYk,Xk n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1. (80) Equivalently, we can write
h
Jk|k(ξ, η)i
i,j= EYk,Xk
{L(Yk; Xk+ hnxξ+i, Xk)L(Yk; Xk+ hnxη+j, Xk)} − 1 = EYk,Xk n Kξ(xξ+1, yξ; xξ+ h (i) ξ , xξ; xξ−1)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1. (81) For ξ = η = 0 (and k ≥ 1) we have
h Jk+1|k(0, 0)i i,j= EYk,Xk+1{L(Yk; Xk+1+ hi , Xk+1)L(Yk; Xk+1+ hj, Xk+1)} − 1 = Ex1,x0 n M0(x1; x0+ h (i) 0 , x0)M0(x1; x0+ h (i) 0 , x0) o − 1. (82) This is equal to h Jk|k(0, 0)i i,j= EYk,Xk {L(Yk; Xk+ hi, Xk)L(Yk; Xk+ hj, Xk)} − 1 = Ex1,x0 n M0(x1; x0+ h (i) 0 , x0)M0(x1; x0+ h (i) 0 , x0) o − 1. (83)
Similarly, for ξ = 0 and 0 < η ≤ k − 1 we obtain h Jk+1|k(0, η)i i,j= EYk,Xk+1 {L(Yk; Xk+1+ hi, Xk+1)L(Yk; Xk+1+ hnxη+j, Xk+1)} − 1 = EYk,Xk n M0(x1; x0+ h (i) 0 , x0)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1, (84)
but this is equal to h
Jk|k(0, η)i
i,j = EYk,Xk{L(Yk; Xk+ hi, Xk)L(Yk; Xk+ hnxη+j, Xk)} − 1 = EYk,Xk n M0(x1; x0+ h (i) 0 , x0)Kη(xη+1, yη; xη+ h(j)η , xη; xη−1) o − 1. (85)
Essentially the same reasoning applies to show that h Jk+1|k(ξ, 0)i i,j = h Jk|k(ξ, 0)i i,j (86)
holds, where 0 < ξ ≤ k − 1. This concludes the proof of Lemma 10.
We partition the prediction information matrix Jk+1|k at time k + 1 as follows
Jk+1|k= Ak+1|k Bk+1|k Ck+1|k Dk+1|k BT k+1|k J k+1|k(k − 1, k − 1) Jk+1|k(k − 1, k) Jk+1|k(k − 1, k + 1) CT k+1|k J k+1|k(k, k − 1) Jk+1|k(k, k) Jk+1|k(k, k + 1) DTk+1|k Jk+1|k(k + 1, k − 1) Jk+1|k(k + 1, k) Jk+1|k(k + 1, k + 1) . (87)
The elements in this matrix can be simplified as follows Dk+1|k Jk+1|k(k − 1, k + 1) Lemma 7 = 0 .. . 0 , (88) Ck+1|k Jk+1|k(k − 1, k) Lemma 8,9 = 0 Jk|k(k − 1, k) , (89) and A k+1|k Bk+1|k BT k+1|k J k+1|k(k − 1, k − 1) Lemma 10 = A k−1|k−1 Bk−1|k−1 BT k−1|k−1 J k|k(k − 1, k − 1) , (90)
yielding Jk+1|k= Ak−1|k−1 Bk−1|k−1 0 BT k−1|k−1 J k|k(k − 1, k − 1) Jk|k(k − 1, k) 0 Jk|k(k, k − 1) Jk+1|k(k, k) 0 0 Jk+1|k(k, k + 1) 0 0 Jk+1|k(k + 1, k) Jk+1|k(k + 1, k + 1) . (91)
Block-matrix inversion gives
Jk+1|k= Jk+1|k(k + 1, k + 1) − 0 0 Jk+1|k(k, k + 1) T Ak−1|k−1 Bk−1|k−1 0 BTk−1|k−1 Jk|k(k − 1, k − 1) Jk|k(k − 1, k) 0 Jk|k(k, k − 1) Jk+1|k(k, k) −1 × 0 0 Jk+1|k(k, k + 1) = Jk+1|k(k + 1, k + 1) − Jk+1|k(k + 1, k)hJk+1|k(k, k) − Jk|k(k, k − 1)hJk|k(k − 1, k − 1) −BTk−1|k−1A−1k−1|k−1Bk−1|k−1 i−1 Jk|k(k − 1, k) −1 Jk+1|k(k, k + 1) = Jk+1|k(k + 1, k + 1) − Jk+1|k(k + 1, k)hJk+1|k(k, k) − Jk|k(k, k − 1)hJk|k(k − 1, k − 1) −Jk−1|k−1(k − 1, k − 1) + J k−1|k−1 i−1 Jk|k(k − 1, k) −1 Jk+1|k(k, k + 1) = Jk+1|k(k + 1, k + 1) − Jk+1|k(k + 1, k)hJk+1|k(k, k) − Jk|k(k, k) + Jk|k i−1 Jk+1|k(k, k + 1) (92) The (i, j)-th elements of the matrices Jk+1|k(k + 1, k + 1), Jk+1|k(k + 1, k) and Jk+1|k(k, k) can be simplified as follows h Jk+1|k(k + 1, k + 1)i i,j= EYk,Xk+1L(Yk ; Xk+1+ hnx(k+1)+i, Xk+1)L(Yk; Xk+1+ hnx(k+1)+j, Xk+1) − 1 = EnNk+1(xk+1+ h (i) k+1, xk+1; xk)Nk+1(xk+1+ h (j) k+1, xk+1; xk) o − 1 = E ( p(xk+1+ h (i) k+1|xk)p(xk+1+ h (j) k+1|xk) p2(x k+1|xk) ) − 1, (93a) h Jk+1|k(k + 1, k)i
i,j= EYk,Xk+1L(Yk; Xk+1+ hnx(k+1)+i, Xk+1)L(Yk; Xk+1+ hnxk+j, Xk+1) − 1 = E n N1(x1+ h (i) 1 , x1; x0)M0(x1; x0+ h (j) 0 ; x0) o − 1, k = 0, E n Nk+1(xk+1+ h (i) k+1, xk+1; xk)Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o − 1, k > 0, = E p(x1+h(i)1 |x0)p(x1|x0+h(j)0 )p(x0+h(j)0 ) p2(x 1|x0)p(x0) − 1, k = 0, E p(xk+1+h(i)k+1|xk)p(xk+1|xk+h(j)k )p(xk+h(j)k |xk−1) p2(xk+1|xk)p(xk|xk−1) − 1, k > 0, =hJk+1|k+1(k + 1, k)i i,j (93b) and h Jk+1|k(k, k)i i,j= EYk,Xk+1
{L(Yk; Xk+1+ hnxk+i, Xk+1)L(Yk; Xk+1+ hnxk+j, Xk+1)} − 1
= E n M0(x1; x0+ h (i) 0 , x0)M0(x1; x0+ h (j) 0 , x0) o − 1, k = 0, E n Kk(xk+1, yk; xk+ h (i) k , xk; xk−1)Kk(xk+1, yk; xk+ h (j) k , xk; xk−1) o − 1, k > 0, = hJk+1|k+1(k, k)i i,j . (93c)
3
Recursive Computation of Smoothing Bound
Theorem 3. The MSE matrix for the smoothing problem is bounded below by
Ex`,YT (x`−xb`(YT))(·)
T H(`, `) J
`|T −1
HT(`, `), (94)
where 0 ≤ ` < T and the information matrix J`|T can be computed recursively as
J`|T = h J`|`+ JT |T(`, `) − J`|`(`, `) i − JT |T(`, ` + 1) × J`+1|T+ JT |T(` + 1, `) h J`|`+ JT |T(`, `) − J`|`(`, `) i−1 JT |T(`, ` + 1) −1 JT |T(` + 1, `), (95) with initialization JT |T. Proof. LetJT |Tt
1:t2,t3:t4 denote the sub-matrix of J
T |T that contains the rows that correspond to time instance
t1 to t2 and the columns that correspond to time instance t3 to t4. We decompose JT |T into blocks which
correspond to time instants 0, 1, . . . , ` and ` + 1, ` + 2, . . . , T with ` < T , yielding
JT |T = " JT |T 0:`,0:` J T |T 0:`,`+1:T JT |T `+1:T ,0:` J T |T `+1:T ,`+1:T # , (96) where h JT |Ti 0:`,0:`= A B BT JT |T(`, `) , (97a) h JT |Ti 0:`,`+1:T = 0 0 JT |T(`, ` + 1) 0 (97b) and h JT |Ti `+1:T ,`+1:T = JT |T(` + 1, ` + 1) JT |T(` + 1, ` + 2) 0 JT |T(` + 2, ` + 1) . .. . .. . .. JT |T(T − 1, T ) 0 JT |T(T, T − 1) JT |T(T, T ) . (97c)
Similarly, the inverseJT |T−1 can be decomposed according to
h JT |Ti −1 = h JT |T−1i 0:`,0:` h JT |T−1i 0:`,`+1:T h JT |T−1i `+1:T ,0:` h JT |T−1i `+1:T ,`+1:T . (98)
We further note that the information matrix J`|`for ` < T can be partitioned as
J`|`= " e A Be e BT J`|`(`, `) # , (99)
such that the information sub-matrix J`|`for estimating x` is given by
J`|`= J`|`(`, `) − eBTAe−1B.e (100) The matrices A = JT |T
0:`−1,0:`−1 and eA = J
`|`