{"id":750409,"date":"2021-05-25T07:53:15","date_gmt":"2021-05-25T14:53:15","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/?post_type=msr-research-item&#038;p=750409"},"modified":"2021-07-08T11:18:33","modified_gmt":"2021-07-08T18:18:33","slug":"directions-in-ml-latent-stochastic-differential-equations-an-unexplored-model-class-talk","status":"publish","type":"msr-video","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/video\/directions-in-ml-latent-stochastic-differential-equations-an-unexplored-model-class-talk\/","title":{"rendered":"Directions in ML: Latent Stochastic Differential Equations: An Unexplored Model Class [Talk]"},"content":{"rendered":"<p>We show how to do gradient-based stochastic variational inference in stochastic differential equations (SDEs), in a way that allows the use of adaptive SDE solvers. This allows us to scalably fit a new family of richly-parameterized distributions over irregularly-sampled time series. We apply latent SDEs to motion capture data, and to demonstrate infinitely-deep Bayesian neural networks. We also discuss the pros and cons of this barely-explored model class, comparing it to Gaussian processes and neural processes.<\/p>\n<p>Learn more about the <a href=\"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/event\/directions-in-ml\/\">2020-2021 Directions in ML: AutoML and Automating Algorithms virtual speaker series ><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We show how to do gradient-based stochastic variational inference in stochastic differential equations (SDEs), in a way that allows the use of adaptive SDE solvers. This allows us to scalably fit a new family of richly-parameterized distributions over irregularly-sampled time series. We apply latent SDEs to motion capture data, and to demonstrate infinitely-deep Bayesian neural [&hellip;]<\/p>\n","protected":false},"featured_media":750412,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_hide_image_in_river":0,"footnotes":""},"research-area":[13561,13556],"msr-video-type":[],"msr-locale":[268875],"msr-post-option":[],"msr-session-type":[],"msr-impact-theme":[],"msr-pillar":[],"msr-episode":[],"msr-research-theme":[],"class_list":["post-750409","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/6iEjF08xgBg","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/750409","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/750409\/revisions"}],"predecessor-version":[{"id":750418,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/750409\/revisions\/750418"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media\/750412"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=750409"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=750409"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=750409"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=750409"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=750409"},{"taxonomy":"msr-session-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-session-type?post=750409"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=750409"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=750409"},{"taxonomy":"msr-episode","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-episode?post=750409"},{"taxonomy":"msr-research-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-theme?post=750409"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}