AIAI Seminar - 25 November 2024 - Cathy Yi-Hsuan Chen Title: Random forest weighted local manifold estimation Abstract: I introduce a novel approach for local manifold estimation using random forest-based kernel weights. Traditional methods, such as nonparametric kernel smoothing, often suffer from the curse of dimensionality. In contrast, our method addresses this limitation by implicitly learning forest weights that closely approximate oracle weights. I propose the Gradient Forest Algorithm, which recursively partitions subsamples based on a manifold-adaptive splitting criterion. This process generates a forest of trees, each capturing local geometric structures embedded in the ambient space. By leveraging random subsampling and recursive partitioning, the algorithm produces adaptive neighborhoods that reflect the intrinsic heterogeneity of the data. The method is particularly well-suited for data with complex geometric properties and high intrinsic dimensionality, where existing local smoothing techniques may struggle. The proposed forest-based ensemble mitigates the high variance associated with individual trees, leading to more stable estimates. This research extends random forest methods by introducing a novel splitting criterion that adapts to the intrinsic properties of data. Bio: Cathy Yi Hsuan Chen is a professor at the Adam Smith Business School, University of Glasgow. She is a fellow of German Econometric Association since 2024. Previously, she served as the Mercator Fellow of International Research Training Group 1792 in Germany until March 2023. Cathy has authored numerous publications that are highly regarded in the academic community. Her papers are known for their depth of theoretical analysis and wide-ranging scope, making them highly impactful and appearing in top econometric journals. Cathy's research interests are focused on the intersection of machine learning approaches, econometrics, data science and finance. She is a co-PI of “Privacy-preserving Data Sharing and Trading Ecosystem for Distributed Wireless IoT Networks” founded by the Engineering and Physical Sciences Research Council (EPSRC) in the UK. She is also a co-PI in the AI in Finance in FinTech Action, founded by European Cooperation in Science and Technology. She represents the UK government's Department of International Trade for reviewing FinTech awards. Nov 25 2024 14.00 - 15.00 AIAI Seminar - 25 November 2024 - Cathy Yi-Hsuan Chen AIAI Seminar hosted by Cathy Yi-Hsuan Chen IF-G.03
AIAI Seminar - 25 November 2024 - Cathy Yi-Hsuan Chen Title: Random forest weighted local manifold estimation Abstract: I introduce a novel approach for local manifold estimation using random forest-based kernel weights. Traditional methods, such as nonparametric kernel smoothing, often suffer from the curse of dimensionality. In contrast, our method addresses this limitation by implicitly learning forest weights that closely approximate oracle weights. I propose the Gradient Forest Algorithm, which recursively partitions subsamples based on a manifold-adaptive splitting criterion. This process generates a forest of trees, each capturing local geometric structures embedded in the ambient space. By leveraging random subsampling and recursive partitioning, the algorithm produces adaptive neighborhoods that reflect the intrinsic heterogeneity of the data. The method is particularly well-suited for data with complex geometric properties and high intrinsic dimensionality, where existing local smoothing techniques may struggle. The proposed forest-based ensemble mitigates the high variance associated with individual trees, leading to more stable estimates. This research extends random forest methods by introducing a novel splitting criterion that adapts to the intrinsic properties of data. Bio: Cathy Yi Hsuan Chen is a professor at the Adam Smith Business School, University of Glasgow. She is a fellow of German Econometric Association since 2024. Previously, she served as the Mercator Fellow of International Research Training Group 1792 in Germany until March 2023. Cathy has authored numerous publications that are highly regarded in the academic community. Her papers are known for their depth of theoretical analysis and wide-ranging scope, making them highly impactful and appearing in top econometric journals. Cathy's research interests are focused on the intersection of machine learning approaches, econometrics, data science and finance. She is a co-PI of “Privacy-preserving Data Sharing and Trading Ecosystem for Distributed Wireless IoT Networks” founded by the Engineering and Physical Sciences Research Council (EPSRC) in the UK. She is also a co-PI in the AI in Finance in FinTech Action, founded by European Cooperation in Science and Technology. She represents the UK government's Department of International Trade for reviewing FinTech awards. Nov 25 2024 14.00 - 15.00 AIAI Seminar - 25 November 2024 - Cathy Yi-Hsuan Chen AIAI Seminar hosted by Cathy Yi-Hsuan Chen IF-G.03
Nov 25 2024 14.00 - 15.00 AIAI Seminar - 25 November 2024 - Cathy Yi-Hsuan Chen AIAI Seminar hosted by Cathy Yi-Hsuan Chen
