Abstract. Given a set X of sequences over a nite alphabet, we investigate the following three quantities. (i) The feasible predictability of X is the highest success ratio that a polynomial-time randomized predictor can achieve on all sequences in X. (ii) The deterministic feasible predictability of X is the highest success ratio that a polynomial-time deterministic predictor can achieve on all sequences in X. (iii) The feasible dimension of X is the polynomial-time eectivization of the classical Hausdor dimension (\fractal dimension") of X. Predictability is known to be stable in the sense that the feasible predictability of X[Y is always the minimum of the feasible predictabilities of X and Y. We show that deterministic predictability also has this property if X and Y are computably presentable. We show that deterministic predictability coincides with predictability on singleton sets. Our main theorem states that the feasible dimension of X is bounded above by the maximum entropy of the predictability of X and bounded below by the segmented self-information of the predictability of X, and that these bounds are tight. 1
|
4364
|
Elements of Information Theory
– Cover, Thomas
- 1991
|
|
253
|
Fractal Geometry. Mathematical Foundations and Applications
– Falconer
- 1990
|
|
240
|
The definition of random sequences
– Martin-Löf
- 1966
|
|
228
|
How to use expert advice
– Cesa-Bianchi, Freund, et al.
- 1997
|
|
159
|
Structural Complexity I
– Balc'azar, D'iaz, et al.
- 1988
|
|
122
|
Zuf"alligkeit und Wahrscheinlichkeit
– Schnorr
- 1971
|
|
115
|
Universal prediction of individual sequences
– Feder, Merhav, et al.
- 1992
|
|
85
|
Universal prediction
– Merhav, Feder
- 1998
|
|
77
|
A game of prediction with expert advice
– Vovk
- 1998
|
|
68
|
Dimension in complexity classes
– Lutz
- 2003
|
|
62
|
A unified approach to the definition of random sequences
– Schnorr
- 1971
|
|
47
|
A new interpretation of information rate
– Kelly
- 1956
|
|
36
|
Classes of recursively enumerable sets and degrees of unsolvability, Zeit
– Martin
- 1966
|
|
31
|
A tight upper bound on Kolmogorov complexity and uniformly optimal prediction
– Staiger
- 1998
|
|
30
|
and the constructive dimension of individual sequences
– Gales
- 2000
|
|
27
|
Hausdorff dimension in exponential time
– Ambos-Spies, Merkle, et al.
- 2001
|
|
24
|
Fractal dimension and logarithmic loss unpredictability
– Hitchcock
|
|
20
|
On tables of random numbers
– Kolmogorov
- 1963
|
|
18
|
Finite-state dimension
– Dai, Lathrop, et al.
|
|
16
|
On prediction of individual sequences
– Cesa-Bianchi, Lugosi
- 1999
|
|
16
|
Algorithmic approach to the prediction problem
– Ryabko
- 1993
|
|
15
|
Certain results in coding theory for noisy channels
– Shannon
- 1957
|
|
13
|
A new interpretation of von Mises' concept of a random sequence. Zeitschrift fur Mathematische Logik und Grundlagen der Mathematik
– Loveland
- 1966
|
|
13
|
Gambling using a finite state machine
– Feder
- 1991
|
|
12
|
A uni approach to the de of random sequences
– Schnorr
- 1971
|
|
11
|
The dimensions of individual strings and sequences. Information and Computation
– Lutz
- 2002
|
|
10
|
Finite-state dimension. Theoretical Computer Science
– Dai, Lathrop, et al.
- 2004
|
|
9
|
Dimension und ausseres Mass
– Hausdor
- 1919
|
|
8
|
Noiseless coding of combinatorial sources
– Ryabko
- 1986
|
|
7
|
Structural Complexity I (second edition
– Balcazar, Daz, et al.
- 1995
|
|
6
|
Dimension und ausseres
– Hausdor
- 1919
|
|
6
|
On relations between dierent algorithmic de of randomness
– Shen
- 1989
|
|
6
|
Kolmogorov complexity and Hausdor dimension
– Staiger
- 1993
|
|
4
|
Noiseless coding of combinatorial sources. Problems of Information Transmission
– Ryabko
- 1986
|
|
4
|
The complexity and eectiveness of prediction problems
– Ryabko
- 1994
|
|
4
|
The nonprobabilistic approach to learning the best prediction
– Ryabko
- 2002
|
|
3
|
Gambling using a state machine
– Feder
- 1991
|
|
2
|
Hausdor# dimension as a new dimension in source coding and predicting
– Ryabko, Suzuki, et al.
- 1999
|
|
1
|
Prediction and dimension of products and convex combinations
– Fortnow, Hitchcock, et al.
|
|
