Abstract: Generative Adversarial Networks are becoming a fundamental tool in Machine Learning, in particular in the context of improving the stability of deep neural networks.
At the same time, recent advances in Quantum Computing have shown that, despite the absence of a fault-tolerant quantum computer so far, quantum techniques are providing exponential advantage over their classical counterparts.
We develop a fully connected Quantum Generative Adversarial network and show how it can be applied in Mathematical Finance, with a particular focus on volatility modelling.
Quantitative Research & Development Lead, ADIA
Alexei Kondratyev: Quantitative Research & Development Lead, ADIA
Alexei Kondratyev is Quantitative Research and Development Lead at Abu Dhabi Investment Authority (ADIA). Prior to joining ADIA in July 2021, he held quantitative research and data analytics positions at Standard Chartered, Barclays Capital and Dresdner Bank. Alexei holds MSc in Theoretical Physics from Taras Shevchenko National University of Kiev and PhD in Mathematical Physics from the Institute for Mathematics, National Academy of Sciences of Ukraine. He was the recipient of 2019 Risk magazine Quant of the Year award.
Associate Director, Quantitative Analyst, Model Validation, Banco Santander
Ángel Rodríguez-Rozas: Associate Director, Quantitative Analyst, Model Validation, Banco Santander
Ángel Rodríguez Rozas holds a Ph.D. in Computational and Applied Mathematics from the University of Lisbon and an M.Sc. in Artificial Intelligence from the Universitat Rovira i Virgili (URV) and the Polytechnic University of Catalonia (UPC). He has authored more than 20 research articles in international peer-reviewed journals in many different areas, including artificial intelligence, numerical methods for PDEs, high-performance computing, plasma physics, the finite element method, seismic wave propagation, and oil&gas simulation and inversion of petrophysical measurements.
Ángel joined Banco Santander in 2018 where he is working as a Quant Analyst in the Internal Validation team, within the Risk Department. As part of his role, Ángel is responsible for leading the design and development of a numerical library for the internal validation of pricing models, including interest rates, FX, credit, commodities, equity, inflation, and xVA. His research efforts are currently focusing on the finance industry, investigating efficient numerical methods (Quasi- and Monte Carlo methods, Finite Elements) and quantum computing algorithms (digital and analog) for the pricing of financial derivatives.
XVA and Credit Derivative Quant, Daiwa Capital Markets
Assad Bouayoun: XVA and Credit Derivative Quant, Daiwa Capital Markets
Assad Bouayoun is a senior XVA Quantitative Analyst with more than 15 years’ experience in leading banks. He has designed industry standard hedging and pricing systems, first in equity derivative at Commerzbank, then in credit derivatives at Credit Agricole, in XVA at Lloyds in Model Validation at RBS in Model Development. Assad has an extensive experience in developing enterprise wide analytics to improve the financial management of derivative portfolios, in particular large scale hybrid Monte-Carlo and Exposure computation. Assad is currently building the prototype of a new XVA platform integrating cutting-edge technologies (GPU, Cloud computing) and numerical methods (AAD) to enable fast and accurate XVA and sensitivities computation. He holds a MSc in Mathematical Trading and Finance from CASS business school and a Master in Applied Mathematics and Computer Science from Université de Technologie de Compiegne (France).
Lead Data Scientist, Applied R&D, Barclays
Dimitrios Emmanoulopoulos: Lead Data Scientist, Applied R&D, Barclays
- This talk presents a simple practical approach to improve asset allocation by combining the human and artificial intelligence
- The method can be used by portfolio managers to both learn from each other and remove their potential sector or factor biases
- The method involves a two-step procedure involving both the inverse reinforcement learning (IRL) and direct RL steps
- At the IRL step, we use the historical funds holdings data to infer the objective (reward) function of their portfolio strategies
- At the RL step, we use a direct RL algorithm called G-learner to improve the portfolio performance by finding the optimal asset allocation policy.
AI Research Associate, Fidelity Investments
Igor Halperin: AI Research Associate, Fidelity Investments
Igor Halperin is an AI Research Associate at Fidelity Investments. His research focuses on using methods of reinforcement learning, information theory, neuroscience and physics for financial problems such as portfolio optimization, dynamic risk management, and inference of sequential decision-making processes of financial agents. Igor has an extensive industrial and academic experience in statistical and financial modeling, in particular in the areas of option pricing, credit portfolio risk modeling, portfolio optimization, and operational risk modeling. Prior to joining Fidelity, Igor worked as a Research Professor of Financial Machine Learning at NYU Tandon School of Engineering. Before that, Igor was an Executive Director of Quantitative Research at JPMorgan, and a quantitative researcher at Bloomberg LP. Igor has published numerous articles in finance and physics journals, and is a frequent speaker at financial conferences. He has co-authored the books “Machine Learning in Finance: From Theory to Practice” (Springer 2020) and “Credit Risk Frontiers” (Bloomberg LP, 2012). Igor has a Ph.D. in theoretical high energy physics from Tel Aviv University, and a M.Sc. in nuclear physics from St. Petersburg State Technical University.
Founder & CEO, Riskfuel
Ryan Ferguson: Founder & CEO, Riskfuel
Ryan is Founder and CEO at Riskfuel, a capital markets focused startup that is developing ultra-fast AI-based valuation technologies.Previously, Ryan was Managing Director and Head of Securitization, Credit Derivatives and XVA at Scotiabank. Prior roles have included credit correlation trading and managing the equity derivatives trading desk. Ryan began his career with positions in risk management and financial engineering. Ryan has a PhD in Physics from Imperial College, and a BASc and MASc in Electrical Engineering from the University of Waterloo.
Ioana Boier: Independent
I have a Ph.D. in Computer Science from Purdue University. In addition, I have completed graduate coursework in Financial Mathematics at NYU and Big Data at Harvard University. Prior to joining Citadel, I was a Director in the Global Markets Division at BNP Paribas where I managed the Interest Rate Options & Inflation quantitative research team. Before transitioning into Finance, I was a research staff member at the IBM T. J. Watson Research Center.
- We’ll be introducing some of the applications for NLP within financial markets including some stylized examples around the recent coronavirus pandemic
- We’ll present some case studies including using macro based examples from Fed communications and also looking at machine readable news from the Financial Times
Saeed Amen: Founder: Cuemacro
Saeed has a decade of experience creating and successfully running systematic trading models at Lehman Brothers and Nomura. He is the founder of Cuemacro, Cuemacro is a company focused on understanding macro markets from a quantitative perspective. He is the author of ‘Trading Thalesians – What the ancient world can teach us about trading today’ (Palgrave Macmillan), and graduated with a first class honours master’s degree from Imperial College in Mathematics& Computer Science.
Abstract: In recent years, various notions of capacity and complexity have been proposed for characterizing the generalization properties of stochastic gradient descent (SGD) in deep learning. Some of the popular notions that correlate well with the performance on unseen data are (i) the flatness of the local minimum found by SGD, which is related to the eigenvalues of the Hessian, (ii) the ratio of the stepsize to the batch-size, which essentially controls the magnitude of the stochastic gradient noise, and (iii) the tail-index, which measures the heaviness of the tails of the network weights at convergence. In this talk, we argue that these three seemingly unrelated perspectives for generalization are deeply linked to each other. We claim that depending on the structure of the Hessian of the loss at the minimum, and the choices of the algorithm parameters, the distribution of the SGD iterates will converge to a heavy-tailed stationary distribution. We rigorously prove this claim in the setting of a simple linear regression problem. We further characterize the behavior of the tails with respect to algorithm parameters, the dimension, and the curvature. We then translate our results into insights about the behavior of SGD in deep learning. We support our theory with experiments conducted on synthetic data, fully connected, and convolutional neural networks.
Associate Professor, Florida State University
Lingjiong Zhu: Associate Professor, Florida State University
Lingjiong Zhu got his BA from University of Cambridge in 2008 and PhD from New York University in 2013. He worked at Morgan Stanley and University of Minnesota before joining the faculty at Florida State University in 2015. His research interests include applied probability, data science, financial engineering and operations research. His works have been published in many high-profile conferences and journals including NeurIPS, ICML, Journal of Machine Learning Research, Annals of Applied Probability, Finance and Stochastics, SIAM Journal on Financial Mathematics and Operations Research.