Hilbert Space Representations of $m$-Dependent Processes
نویسندگان
چکیده
منابع مشابه
Hilbert Space Embeddings of Predictive State Representations
Predictive State Representations (PSRs) are an expressive class of models for controlled stochastic processes. PSRs represent state as a set of predictions of future observable events. Because PSRs are defined entirely in terms of observable data, statistically consistent estimates of PSR parameters can be learned efficiently by manipulating moments of observed training data. Most learning algo...
متن کاملProjective Group Representations in Quaternionic Hilbert Space
We extend the discussion of projective group representations in quaternionic Hilbert space which was given in our recent book. The associativity condition for quaternionic projective representations is formulated in terms of unitary operators and then analyzed in terms of their generator structure. The multi–centrality and centrality assumptions are also analyzed in generator terms, and implica...
متن کاملA Hilbert Space of Stationary Ergodic Processes
Identifying meaningful signal buried in noise is a problem of interest arising in diverse scenarios of datadriven modeling. We present here a theoretical framework for exploiting intrinsic geometry in data that resists noise corruption, and might be identifiable under severe obfuscation. Our approach is based on uncovering a valid complete inner product on the space of ergodic stationary finite...
متن کاملCointegrated linear processes in Hilbert space
Consider a sequence X = (X0,X1, . . .) of random elements of a real separable Hilbert space H , whose rst dierence is a standard linear process with long run covariance operator Λ. We show that, under a mild summability condition, the set of vectors x ∈ H for which 〈Xt ,x〉 is stationary given a suitable initialization X0 is the kernel of Λ. We call this space the cointegrating space, and its ...
متن کاملZakai Equations for Hilbert Space Valued Processes*
versity A state process is described by either a discrete time Hilbert space valued process, or a stochastic differential equation in Hilbert space. The state is observed through a finite dimensional process. Using a change of measure and a Fusive theorem the Zakai equation is obtained in discrete or continuous time. A risk sensitive state estimate is also defined.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Annals of Probability
سال: 1993
ISSN: 0091-1798
DOI: 10.1214/aop/1176989130