#### Filter Results:

- Full text PDF available (20)

#### Publication Year

1992

2016

- This year (0)
- Last 5 years (3)
- Last 10 years (8)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Gusztáv Morvai, Sidney J. Yakowitz, Paul H. Algoet
- IEEE Trans. Information Theory
- 1997

The conditional distribution of the next outcome given the infinite past of a stationary process can be inferred from finite but growing segments of the past. Several schemes are known for… (More)

- László Györfi, Gábor Lugosi, Gusztáv Morvai
- IEEE Trans. Information Theory
- 1999

We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show… (More)

- László Györfi, Gusztáv Morvai, Sidney J. Yakowitz
- IEEE Trans. Information Theory
- 1998

This study concerns problems of time-series forecasting under the weakest of assumptions. Related results are surveyed and are points of departure for the developments here, some of which are new and… (More)

- Gusztáv Morvai, Sidney J. Yakowitz, László Györfi
- ArXiv
- 2007

Nonparametric inference for ergodic, stationary time series. Abstract The setting is a stationary, ergodic time series. The challenge is to construct a sequence of functions, each based on only… (More)

- Gusztáv Morvai
- ArXiv
- 2007

The forward prediction problem for a binary time series {X n } ∞ n=0 is to estimate the probability that X n+1 = 1 based on the observations X i , 0 ≤ i ≤ n without prior knowledge of the… (More)

- Gusztáv Morvai, Benjamin Weiss
- ArXiv
- 2002

The forecasting problem for a stationary and ergodic binary time series {Xn}n=0 is to estimate the probability that Xn+1 = 1 based on the observations Xi, 0 ≤ i ≤ n without prior knowledge of the… (More)

- Gusztáv Morvai, Benjamin Weiss
- IEEE Transactions on Information Theory
- 2005

Estimators /spl chi//sub n/(X/sub 0/, X/sub 1/, ..., X/sub n/), are described which, when applied to an unknown stationary process taking values from a countable alphabet /spl chi/, converge almost… (More)

- Andrew B. Nobel, Gusztáv Morvai, Sanjeev R. Kulkarni
- IEEE Trans. Information Theory
- 1998

This paper considers estimation of a univariate density from an individual numerical sequence. It is assumed that (i) the limiting relative frequencies of the numerical sequence are governed by an… (More)

- Gusztáv Morvai, Benjamin Weiss
- ArXiv
- 2007

Finitarily Markovian processes are those processes {Xn}n=−∞ for which there is a finite K (K = K({Xn} 0 n=−∞) such that the conditional distribution of X1 given the entire past is equal to the… (More)

- Gusztáv Morvai, Benjamin Weiss
- ArXiv
- 2005

Let {Xn} be a stationary and ergodic time series taking values from a finite or countably infinite set X . Assume that the distribution of the process is otherwise unknown. We propose a sequence of… (More)