Conditioning of Banach Space Valued Gaussian Random Variables: An Approximation Approach Based on Martingales
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910841620660224 |
|---|---|
| author | Steinwart, Ingo |
| author_facet | Steinwart, Ingo |
| contents | We investigate the conditional distributions of two Banach space valued, jointly Gaussian random variables. In particular, we show that these conditional distributions are again Gaussian and that their means and covariances can be determined by a general finite dimensional approximation scheme. Here, it turns out that the covariance operators occurring in this scheme converge with respect to the nuclear norm and that the conditional probabilities converge weakly. Furthermore, we discuss how our approximation scheme can be implemented in several classes of important Banach spaces such as (reproducing kernel) Hilbert spaces, spaces of continuous functions, and other spaces consisting of functions. As an example, we then apply our general results to the case of continuous Gaussian processes that are conditioned to partial but infinite observations of their paths. Here we show that conditioning on sufficiently rich, increasing sets of finitely many observations leads to consistent approximations, that is, both the mean and covariance functions converge uniformly and the conditional probabilities converge weakly. Moreover, we discuss how these results improve our understanding of the popular Gaussian processes for machine learning. From a technical perspective our results are based upon a Banach space valued martingale approach for regular conditional probabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03453 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Conditioning of Banach Space Valued Gaussian Random Variables: An Approximation Approach Based on Martingales Steinwart, Ingo Probability Machine Learning Statistics Theory Primary 60G15, Secondary 60B10, 60B11, 62F15, 62G05, 62G20, 28C20, 68T05 We investigate the conditional distributions of two Banach space valued, jointly Gaussian random variables. In particular, we show that these conditional distributions are again Gaussian and that their means and covariances can be determined by a general finite dimensional approximation scheme. Here, it turns out that the covariance operators occurring in this scheme converge with respect to the nuclear norm and that the conditional probabilities converge weakly. Furthermore, we discuss how our approximation scheme can be implemented in several classes of important Banach spaces such as (reproducing kernel) Hilbert spaces, spaces of continuous functions, and other spaces consisting of functions. As an example, we then apply our general results to the case of continuous Gaussian processes that are conditioned to partial but infinite observations of their paths. Here we show that conditioning on sufficiently rich, increasing sets of finitely many observations leads to consistent approximations, that is, both the mean and covariance functions converge uniformly and the conditional probabilities converge weakly. Moreover, we discuss how these results improve our understanding of the popular Gaussian processes for machine learning. From a technical perspective our results are based upon a Banach space valued martingale approach for regular conditional probabilities. |
| title | Conditioning of Banach Space Valued Gaussian Random Variables: An Approximation Approach Based on Martingales |
| topic | Probability Machine Learning Statistics Theory Primary 60G15, Secondary 60B10, 60B11, 62F15, 62G05, 62G20, 28C20, 68T05 |
| url | https://arxiv.org/abs/2404.03453 |