Adaptive estimation for Hawkes processes; application to genome analysis

Abstract

The aim of this paper is to provide a new method for the detection of either favored or avoided distances between genomic events along DNA sequences. These events are modeled by a Hawkes process. The biological problem is actually complex enough to need a nonasymptotic penalized model selection approach. We provide a theoretical penalty that satisfies an oracle inequality even for quite complex families of models. The consecutive theoretical estimator is shown to be adaptive minimax for H\"{o}lderian functions with regularity in $(1/2,1]$: those aspects have not yet been studied for the Hawkes' process. Moreover, we introduce an efficient strategy, named Islands, which is not classically used in model selection, but that happens to be particularly relevant to the biological question we want to answer. Since a multiplicative constant in the theoretical penalty is not computable in practice, we provide extensive simulations to find a data-driven calibration of this constant. The results obtained on real genomic data are coherent with biological knowledge and eventually refine them.Comment: Published in at http://dx.doi.org/10.1214/10-AOS806 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org

Reactive point processes: A new approach to predicting power failures in underground electrical systems

“…An earthquake elevates the risk of aftershocks, where the magnitude and temporal properties of this elevated risk are determined by the kernel g. Subsequent works (Musmeci and Vere-Jones, 1992;Ogata, 1998) Recently, self exciting point processes have been shown to be e↵ective for genome analysis (Reynaud-Bouret and Schbath, 2010) as well as analyzing and capturing the dynamics and neural spike trains (Krumin et al, 2010). These domains have distinct properties that require unique models (for example, the self-excitation component of the model for DNA sequences replaces geographic distance with a distance between basepairs).…”

Concentration inequalities, counting processes and adaptive statistics

“…This approach leads to the results of [46] for the Hawkes case in a straightforward way. A slightly different approach has been used in [43] for the Aalen case.…”

Nonparametric Markovian Learning of Triggering Kernels for Mutually Exciting and Mutually Inhibiting Multivariate Hawkes Processes

“…Moreover, thanks to the approximation rates of convergence (Proposition 1), triggering kernels can be accurately estimated for large K through maximization of the new objective (7). Finally, the Markov property is an important feature that will allow us to construct the vectors (A K,h,i ) and (B K,h ) with linear complexity.…”