Higher Order KMEs to capture Filtrations of Stochastic Processes
Dec 6, 2021
Speakers
Cristopher Salvi
Speaker · 0 followers
Maud Lemercier
Speaker · 0 followers
Blanka Horvath
Speaker · 0 followers
Theodoros Damoulas
Speaker · 0 followers
Terry Lyons
Speaker · 0 followers
About
Stochastic processes are random variables with values in some space of paths. However, reducing a stochastic process to a path-valued random variable ignores its filtration, i.e. the flow of information carried by the process through time. By conditioning the process on its filtration, we introduce a family of higher order kernel mean embeddings (KMEs) that generalizes the notion of KME to capture additional information related to the filtration. We derive empirical estimators for the associated higher order maximum mean discrepancies (MMDs) and prove consistency. We then construct a filtration-sensitive kernel two-sample test able to capture information that gets missed by the standard MMD test. In addition, leveraging our higher order MMDs we construct a family of universal kernels on stochastic processes that allows to solve real-world calibration and optimal stopping problems in quantitative finance (such as the pricing of American options) via classical kernel-based regression methods. Finally, adapting existing tests for conditional independence to the case of stochastic processes, we design a causal-discovery algorithm to recover the causal graph of structural dependencies among interacting bodies solely from observations of their multidimensional trajectories.Stochastic processes are random variables with values in some space of paths. However, reducing a stochastic process to a path-valued random variable ignores its filtration, i.e. the flow of information carried by the process through time. By conditioning the process on its filtration, we introduce a family of higher order kernel mean embeddings (KMEs) that generalizes the notion of KME to capture additional information related to the filtration. We derive empirical estimators for the associated…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
On the Expected Complexity of Maxout Networks
Watch later
Hanna Tseran, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Investigating generative neural-network models for building pest insect detectors in sticky trap images for the Peruvian horticulture
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Tutorials track at Climate Change Al
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
What Would the Expert do(.)?: Causal Imitation Learning
Watch later
Gokul Swamy, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Automated Dynamic Mechanism Design
Watch later
Hanrui Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Structure from Action: Physical Scene Understanding with Active Interactions
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%