Author:Subscribed: 0Played: 0
Geoff Pleiss is a Postdoctoral researcher at Columbia University, with affiliations in the Department of Statistics and the Zuckerman Institute. He holds a PhD in Computer Science from Cornell University, and is Co-founder and maintainer of the GPyTorch software library. His research places him at the nexus of deep learning, probabilistic modeling, and numerical linear algebra, enabling him to address both of these challenges. One line of his work focuses directly on neural networks, improving their uncertainty estimates while understanding their predictive capabilities through the lens of probabilistic models. Another line focuses on the inductive biases of Gaussian processes (GP), improving their computational efficiency and ultimately replicating their desirable properties in neural networks. This research profile ideally situates him to unite these paradigms, transforming today’s powerful models into general reasoning models. In addition, he has a proven record of coupling his findings with performant and easy-to-use software used widely throughout research and industry, facilitating adoption and innovation in this area.
A Unified Framework for Sequential Decisions with Warren Powell
Warren Powell is Chief Analytics Officer of Optimal Dynamics and Professor Emeritus from Princeton University, where he taught and served as a faculty member in the Department of Operations Research and Financial Engineering since 1981. In the 1980s Powell designed and wrote SYSNET, an interactive optimization model for load planning at Yellow Freight System, where it is still in use after 25 years. He is the founder of Princeton Transportation Consulting Group, which marketed the model as SuperSPIN, stabilizing an industry where 80% of companies went bankrupt in the first post-deregulation decade. SuperSPIN was used in the planning of American Freightways (which became FedEx Freight) and Overnight Transportation (which became UPS Freight). In 1990 Powell founded CASTLE Laboratory which spans research in computational stochastic optimization with applications initially in transportation and logistics. In 2011 he then founded the Princeton laboratory for ENergy Systems Analysis (PENSA) to tackle the rich array of problems in energy systems analysis, and in 2013: this morphed into “CASTLE Labs,” focusing on computational stochastic optimization and learning. In 2017 Powell founded Optimal Dynamics, helping carriers to automate and optimize trucking networks using AI. Motivated by these applications, he developed a method for bridging dynamic programming with math programming to solve very high-dimensional stochastic, dynamic programs using the modeling and algorithmic framework of approximate dynamic programming. He identified four fundamental classes of policies for solving sequential decision problems, integrating fields such as stochastic programming, dynamic programming (including approximate dynamic programming/reinforcement learning), robust optimization, optimal control and stochastic search (to name a few). This work identified a new class of policy called a parametric cost function approximation. His work in industry is balanced by contributions to the theory of stochastic optimization, and machine learning.
Beyond Markowitz With Machine Learning in Portfolio Management with Alejandro Rodriguez Dominguez
Alejandro Rodriguez Dominguez is Head of Quantitative Research and Analysis at Miralta Bank, Madrid. With extensive experience in financial engineering, he leads Data Analytics and Solutions in Quantitative Finance for the group. Through the creation of AI financial solutions for their clients, Alejandro develops data architecture for both regulatory and strategic reporting. Alongside the modeling and implementation of risk management practices for Miralta Bank, he creates data-driven market analysis tools for brokerage clients. Alejandro holds a PhD in Computer Science from the University of Reading, and a Master’s degree in Artificial Intelligence from Munster Technological University. His research interests include Solutions for Continual Learning and Catastrophic Forgetting in AI, Information Geometry and AI, Correlation Dynamics (changes and forecasting), AI for Pricing, and Risk Management of Financial Products, and Systematic Trading Strategies with a focus on Pricing, Nowcasting, Dynamical Systems, and Statistics and Probability. Our conversation focused on the interaction of classic quantitative finance with machine learning, the use of random matrix theory in finance.
Complex Systems and Machine Learning in Molecular Biology with Stefano Zapperi and Caterina La Porta
Stefano Zapperi is Professor of Theoretical Condensed Matter Physics and Coordinator of the Center for Complexity and Biosystems at the University of Milan. He graduated in physics at the University of Rome “La Sapienza” and received his Ph. D. in physics from Boston University. After a postdoctoral position at ESPCI in Paris, he became tenured researcher at INFM at the University Rome and then at the University Modena and Reggio Emilia. He has been invited as visiting scientist or visiting professor in many institutions worldwide. Prof. Zapperi is an expert in the statistical physics of complex systems and has fostered computational and data driven approaches to materials science and biophysics. His most notable contributions include the theory of the Barkhausen noise in magnets, the statistical physics of plasticity and fracture, and recent work on the physics of cancer and protein aggregation. Prof. Zapperi is the recipient of numerous awards including the Marie Curie Excellence Award. He was elected fellow of the American Physical Society and named Finland Distinguished Professor by the Academy of Finland. He organized several international workshops, summer schools and symposia on a variety of interdisciplinary research topics, ranging from the “Physics of Cancer” to Statistical Physics of Materials and Complex Systems. He has been elected member of the council and the executive committee of the Complex Systems Society and acted as chair of the steering committee of the Conference on Complex Systems. In 2018 he co-founded Complexdata alongside Caterina La Porta. Caterina La Porta is professor of General Pathology at the University of Milan where she coordinates the research group Oncolab and is member of the steering committee of the Center for Complexity and Biosystems. In 2018, she co-founded the startup ComplexData where she serves as CEO. During her scientific career, Prof. La Porta published more than 200 papers in international journals mainly on cancer and neurodegenerative diseases, receiving thousands of citations. In the past 15 years, she shifted her interest to quantitative biology and digital health. The focus of her current research activity focuses on understanding cancer heterogeneity using tools from cell biology, biophysics and data science. Her interdisciplinary view of cancer is summarized in a book published by Cambridge University Press in 2017 entitled “The Physics of Cancer”. Prof. La Porta was selected as one of the 100 most important female scientists in Italy (https://100esperte.it/) and was visiting scientist in many universities around the world, including MIT, Cornell University, Aalto University, Rice University, the ENS Paris, the Weizmann Institute of Science and LMU in Germany. Prof. La Porta has a long track record of public outreach activities, including the organization of several editions of the EU Researcher’s night, and is involved in many other science dissemination activities.
Deterministic Chaos and Koopman Theory with Igor Mezić
Igor Mezić is a mechanical engineer, mathematician, and Distinguished Professor of mechanical engineering and mathematics at the University of California, Santa Barbara. He is best known for his contributions to operator theoretic, data-driven approach to dynamical systems theory that he advanced via articles based on Koopman operator theory and his work on the theory of mixing. LINKS: https://en.wikipedia.org/wiki/Igor_Mezićhttps://www.linkedin.com/in/igor-mezi...https://www.researchgate.net/profile/...
Econophysics with Jean-Philippe Bouchaud
Jean-Philippe Bouchaud, a statistical physicist, is a pioneer in econophysics, a research field applying theories and methods originally developed by physicists in order to solve problems in economics, usually those including uncertainty or stochastic processes and nonlinear dynamics. He is the co-founder and chairman of Capital Fund Management, global asset management using quantitative and scientific approaches to financial markets to invest billions of dollars in a systematic way. He is also the Head of Research of CFM and a professor at École Normale Supérieure. We talk about how ideas in dynamical systems theory and complex systems theory, like the ones developed by the 2021 Physics Nobel prize Giorgio Parisi, but also by Michael Fisher and Benoit Mandelbrot, influenced him. We talk about fat tails, Levy flights, and their emergence in both physical and financial systems. We talk about diffusion phenomena, fractional Brownian motion, hyperchaos, the Hurst exponent, and their application in finance. We touch on the wisdom of crowds, the emergence of intelligence in complex systems, their relations with the efficient market hypothesis, and the limits of Markovian modeling of the financial market. We also try to inform policymaking, both aiming at an optimal level of inequality in society and dealing with systematic incentives to push against what Bret Weinstein calls the personal responsibility vortex, therefore criticizing the invisible hand idea by Adam Smith. We close with the use of Artificial Intelligence techniques in finance, focusing on the relationship between Deep Learning, Kernel Methods, and Random Matrix Theory. LINKS: https://crunchdao.com https://en.wikipedia .org/wiki/Jean-Ph...https://www.linkedin.com/in/jean-phil...https://www.cfm.fr/https://scholar.google.com/citations?...