{"672951":{"#nid":"672951","#data":{"type":"event","title":"CSIP Seminar: Normalizing flow neural networks by JKO scheme","body":[{"value":"\u003Ch3\u003E\u003Cstrong\u003ECenter for Signals and Information Processing (CSIP)\u0026nbsp;Seminar\u003C\/strong\u003E\u003C\/h3\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;Friday, February 16,\u0026nbsp;2024\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E\u0026nbsp;3:00 p.m. - 4:00 p.m.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation:\u0026nbsp;\u003C\/strong\u003ECentergy Building 5126.\u0026nbsp;The associated zoom link is:\u0026nbsp;\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/92180566322\u0022 id=\u0022OWA2863be82-4b07-58b3-4fae-86f7e13421d8\u0022 rel=\u0022noopener noreferrer\u0022 target=\u0022_blank\u0022 title=\u0022https:\/\/gatech.zoom.us\/j\/92180566322\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/92180566322\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESpeaker:\u003C\/strong\u003E Chen Xu\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESpeakers\u0027 Title:\u003C\/strong\u003E Operations Research Ph.D. in ISyE\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESeminar Title:\u003C\/strong\u003E\u0026nbsp;Normalizing flow neural networks by JKO scheme\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u0026nbsp;\u003C\/strong\u003EChen Xu is currently a fourth-year Operations Research PhD in ISyE, where he is supervised by Prof. Yao Xie. His current research interests are two-fold. (1) Uncertainty quantification for machine learning models. Specifically, advance conformal prediction as a distribution-free method for arbitrarily complex deep models, especially in the context of time-series modeling. (2) Generative models through flow-based neural networks. Specifically, develop scalable computational tools for problems at the intersection of statistics and optimization, including extensions to high-dimensional optimal transport, distributionally robust optimization, and differential privacy. His works have appeared in top machine learning conferences (e.g., ICML 2021 oral, NeurIPS 2023 spotlight) and journals (e.g., IEEE TPAMI 2023, IEEE JSAIT).\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EBio:\u003C\/strong\u003E Normalizing flow is a class of deep generative models for efficient sampling and likelihood estimation, which achieves attractive performance, particularly in high dimensions. The flow is often implemented using a sequence of invertible residual blocks. Existing works adopt special network architectures and regularization of flow trajectories. In this paper, we develop a neural ODE flow network called JKO-iFlow, inspired by the Jordan-Kinderleherer-Otto (JKO) scheme, which unfolds the discrete-time dynamic of the Wasserstein gradient flow. The proposed method stacks residual blocks one after another, allowing efficient block-wise training of the residual blocks, avoiding sampling SDE trajectories and score matching or variational learning, thus reducing the memory load and difficulty in end-to-end training. We also develop adaptive time reparameterization of the flow network with a progressive refinement of the induced trajectory in probability space to improve the model accuracy further. Experiments with synthetic and real data show that the proposed JKO-iFlow network achieves competitive performance compared with existing flow and diffusion models at a significantly reduced computational and memory cost.\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EChen Xu, a fourth-year Operations Research Ph.D. in ISyE, will present the CSIP Seminar, \u0022Normalizing flow neural networks by JKO scheme\u0022 on February 16, 2024.\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"Featuring Chen Xu, Operations Research Ph.D. in ISyE"}],"uid":"36558","created_gmt":"2024-02-14 20:53:34","changed_gmt":"2024-02-14 20:56:21","author":"zwiniecki3","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-02-16T15:00:00-05:00","event_time_end":"2024-02-16T16:00:00-05:00","event_time_end_last":"2024-02-16T16:00:00-05:00","gmt_time_start":"2024-02-16 20:00:00","gmt_time_end":"2024-02-16 21:00:00","gmt_time_end_last":"2024-02-16 21:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Centergy Building 5126","extras":[],"groups":[{"id":"1255","name":"School of Electrical and Computer Engineering"}],"categories":[],"keywords":[{"id":"192224","name":"CSIP Seminar"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"174045","name":"Graduate students"},{"id":"177814","name":"Postdoc"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EGhazal Kaviani\u003Cbr \/\u003E\r\n\u003Ca href=\u0022gkaviani3@gatech.edu\u0022\u003Egkaviani3@gatech.edu\u003C\/a\u003E\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}