Seminar Series: Women in Data Science and Maths
Seminar Series: Women in Data Science and Maths
  • 17
  • 1 925
A Look Back at 2024: WINDSMATH Seminar Series
Join us in revisiting the highlights of WINDSMATH Seminar's 2024 journey! This video not only celebrates our seminar series but also showcases the inspiring moments from exceptional talks on machine learning and mathematics by leading female researchers in this field. We look forward to your participation and engagement in 2025! #WINDSMATHSeminars #2024Recap
______________________________________________________________________
Song: Upbeat Corporate by Wavecont Music
provided by protunes.net
Video Link: th-cam.com/video/EvEmG8PrLFI/w-d-xo.html
___________________________________________________________________________
āļĄāļļāļĄāļĄāļ­āļ‡: 5

āļ§āļĩāļ”āļĩāđ‚āļ­

Deep Gaussian processes: theory and applications
āļĄāļļāļĄāļĄāļ­āļ‡ 1014 āļ§āļąāļ™āļ—āļĩāđˆāļœāđˆāļēāļ™āļĄāļē
Deep Gaussian processes: theory and applications Speaker: Dr. Aretha Teckentrup Time: 14:00 (GMT), December 17, 2024 Abstract Deep Gaussian processes have proved remarkably successful as a tool for various statistical inference tasks. This success relates in part to the flexibility of these processes and their ability to capture complex, non-stationary behaviours. In this talk, we will introduc...
Dimensionality reduction techniques for optimization problems
āļĄāļļāļĄāļĄāļ­āļ‡ 28āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
Dimensionality reduction techniques for optimization problems Speaker: Prof. Coralia Cartis Time: 14:00 (GMT), November 27, 2024 Abstract Modern applications such as machine learning involve the solution of huge scale nonconvex optimization problems, sometimes with special structure. Motivated by these challenges, we investigate more generally, dimensionality reduction techniques in the variabl...
A level-set approach for control problems arising in energy production and distribution
āļĄāļļāļĄāļĄāļ­āļ‡ 222 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
A level-set approach for control problems arising in energy production and distribution Speaker: Prof. Athena Picarelli Time: 11:00 (GMT), Oct 30, 2024 Abstract The consumption of energy amongst a population often exhibits heterogeneous features, including but not limited to geographical, demographic and seasonality factors. Matching supply and demand is imperative for stable and reliable trans...
The Rise of Reinforcement Learning: from One to Many
āļĄāļļāļĄāļĄāļ­āļ‡ 873 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
The Rise of Reinforcement Learning: from One to Many Speaker: Prof. Niao He Time: 18:00 (BST), September 25, 2024. Abstract Reinforcement learning (RL), combined with deep neural networks, is key to the boom of recent AI breakthroughs from game mastery to control automation. However, their successes are overly reliant on brute-force computing power and engineering tricks, leaving wide gaps betw...
Unveiling the Role of the Wasserstein Distance in Generative Modelling
āļĄāļļāļĄāļĄāļ­āļ‡ 1403 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
Unveiling the Role of the Wasserstein Distance in Generative Modelling Speaker: Prof. Lisa Kreusser Time: 18:00 (BST), September 4, 2024. Abstract Generative models have become very popular over the last few years in the machine learning community. These are generally based on likelihood based models (e.g. variational autoencoders), implicit models (e.g. generative adversarial networks), as wel...
A Look Back at WINDSMATH Seminar Series
āļĄāļļāļĄāļĄāļ­āļ‡ 95 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
Join us in revisiting the highlights of WINDSMATH Seminar's journey! Song: Upbeat Corporate by Wavecont Music provided by protunes.net Video Link: th-cam.com/video/EvEmG8PrLFI/w-d-xo.html
A deep learning analysis of climate change, innovation, and uncertainty
āļĄāļļāļĄāļĄāļ­āļ‡ 607 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
A deep learning analysis of climate change, innovation, and uncertainty Prof. Ruimeng Hu 18:00 (BST), May 29th, 2024 Abstract We study the implications of model uncertainty in a climate-economics framework with three types of capital: “dirty” capital that produces carbon emissions when used for production, “clean” capital that generates no emissions but is initially less productive than dirty c...
AI and the Future of Optimization
āļĄāļļāļĄāļĄāļ­āļ‡ 2198 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
AI and the Future of Optimization Prof. Madeleine Udell 16:00 (BST), Apr 24th, 2024 Abstract Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers, as the expertise required to formulate and solve these problems limits the widespread ad...
AI for Science: Discovering Diverse Classes of Governing Equations in Medicine and Beyond
āļĄāļļāļĄāļĄāļ­āļ‡ 19810 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
AI for Science: Discovering Diverse Classes of Governing Equations in Medicine and Beyond Prof. Mihaela van der Schaar 14:00 (GMT), Feb 26th, 2024 Abstract Artificial Intelligence (AI) offers the promise of revolutionizing the way scientific discoveries are made and significantly accelerating their pace. This is important for numerous fields of study, including medicine. In this talk, I will pr...
A Model-Agnostic Graph Neural Network for Integrating Local and Global Information
āļĄāļļāļĄāļĄāļ­āļ‡ 10411 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
A Model-Agnostic Graph Neural Network for Integrating Local and Global Information Prof. Annie Qu 16:00 (GMT), Jan 30th, 2024 Abstract Graph neural networks (GNNs) have achieved promising performance in a variety of graph focused tasks. Despite their success, the two major limitations of existing GNNs are the capability of learning various-order representations and providing interpretability of...
A Look Back at 2023: WINDSMATH Seminar Series
āļĄāļļāļĄāļĄāļ­āļ‡ 8711 āļŦāļĨāļēāļĒāđ€āļ”āļ·āļ­āļ™āļāđˆāļ­āļ™
Join us in revisiting the highlights of WINDSMATH Seminar's 2023 journey! This video not only celebrates our seminar series but also showcases the inspiring moments from exceptional talks on machine learning and mathematics by leading female researchers in this field. We look forward to your participation and engagement in 2024! #WINDSMATHSeminars #2023Recap Song: Upbeat Corporate by Wavecont M...
Dynamic pricing and learning with Bayesian persuasion| Prof. Shipra Agrawal
āļĄāļļāļĄāļĄāļ­āļ‡ 260āļ›āļĩāļ—āļĩāđˆāđāļĨāđ‰āļ§
Dynamic pricing and learning with Bayesian persuasion Prof. Shipra Agrawal Abstract Modern customers' decisions are intricately shaped not only by their own preferences but also by the associated product information and the offered price. We consider a novel dynamic pricing and learning setting where in addition to setting prices of products in sequential rounds, the seller also ex-ante commits...
On Graph Limits as Models for Interaction Data
āļĄāļļāļĄāļĄāļ­āļ‡ 88āļ›āļĩāļ—āļĩāđˆāđāļĨāđ‰āļ§
Abstract Network data has become a staple in many different applications, ranging from ecology, to neuroscience and systems biology. Its inference will of course depend on the application where we collect the network data, but I will discuss some general principles based on probabilistic symmetries such as permutation invariance. Just like other probabilistic invariances, the distributional inv...
Reinforcement Learning meets Federated Learning and Distributional Robustness
āļĄāļļāļĄāļĄāļ­āļ‡ 273āļ›āļĩāļ—āļĩāđˆāđāļĨāđ‰āļ§
Abstract Reinforcement learning (RL) is garnering significant interest in recent years due to its success in a wide variety of modern applications. However, theoretical understandings on the non-asymptotic sample efficiencies of RL algorithms remain elusive, and are in imminent need to cope with the ever-increasing problem dimensions. In this talk, we discuss our recent progress on understandin...
Mathematics of transfer learning and transfer risk: from medical to financial data analysis
āļĄāļļāļĄāļĄāļ­āļ‡ 126āļ›āļĩāļ—āļĩāđˆāđāļĨāđ‰āļ§
Mathematics of transfer learning and transfer risk: from medical to financial data analysis
The Modern Mathematics of Artificial Intelligence: From Reliable AI to Quantum Computing
āļĄāļļāļĄāļĄāļ­āļ‡ 210āļ›āļĩāļ—āļĩāđˆāđāļĨāđ‰āļ§
The Modern Mathematics of Artificial Intelligence: From Reliable AI to Quantum Computing