The aim of this paper is to address two related estimation problems arising in the setup of hidden state linear time invariant (LTI) state space systems when the dimension of the hidden state is unknown. Namely, the estimation of any finite number of the system's Markov parameters and the estimation of a minimal realization for the system, both from the partial observation of a single trajectory. For both problems, we provide statistical guarantees in the form of various estimation error upper bounds, $\rank$ recovery conditions, and sample complexity estimates. Specifically, we first show that the low $\rank$ solution of the Hankel penalized least square estimator satisfies an estimation error in $S_p$-norms for $p \in [1,2]$ that captures the effect of the system order better than the existing operator norm upper bound for the simple least square. We then provide a stability analysis for an estimation procedure based on a variant of the Ho-Kalman algorithm that improves both the dependence on the dimension and the least singular value of the Hankel matrix of the Markov parameters. Finally, we propose an estimation algorithm for the minimal realization that uses both the Hankel penalized least square estimator and the Ho-Kalman based estimation procedure and guarantees with high probability that we recover the correct order of the system and satisfies a new fast rate in the $S_2$-norm with a polynomial reduction in the dependence on the dimension and other parameters of the problem.

INCE the appearance of the seminal paper [1], NMF has become a popular data decomposition technique due to succesful applications in a still growing number of fields where data are nonnegative, such as pixel intensities in computer vision, amplitude spectra in audio signal analysis and EEG signal analysis, term counts in document clustering problems, and item ratings in collaborative filtering. NMF aims at decompositions, where, and are all nonnegative matrices. Throughout this paper will be regarded as a collection of data samples organized columnwise, as a dictionary of features organized columnwise, and as matrix of coefficients when is projected onto the dictionary. Under assumptions of linearity and nonnegativity, when underlying dimensionality is lower than dimensionality of the original space of the data, dimensionality reduction of the data can effectively be achieved this way. Although the decomposition is nonunique in general, NMF is able to produce strictly additive decompositions perceived as part-based by adding additional bias in the model [1], [2]. To this end, different sparsity promoting regularizers have been proposed for divergence-based NMF [3]. Also, to include higher order data descriptions, many other variants have been developed, e.g.