Realistic Controlled Time Series Generation with Variational Autoencoder
Publications
Publications
Articles
Coupling of Lagrangian mechanics and physics-informed neural networks for the identification of migration dynamics
Model-Aware Automatic Benchmark Generation with Self-Error Instructions for Data-Driven Models
A Dynamic Model of Customers Behavior: Integrating Econophysics and Physics-Informed Neural Networks
Multivariate Time Series Modelling with Neural SDE Driven by Jump Diffusion
TRGAN: A Time-Dependent Generative Adversarial Network for Synthetic Transactional Data Generation
Synthetic Financial Time Series Generation with Regime Clustering
Time-dependent differential privacy for enhanced data protection in synthetic transaction generation
Forecasting Population Migration in Small Settlements Using Generative Models under Conditions of Data Scarcity
Preprints
Mathematical analysis of break-even points and return bounds for option strategies
This manual is designed for self-guided study of options-based trading strategies. It provides information on some of the most well-established strategies and will be beneficial for both beginners and experienced professionals as a short summary. It also contains a number of exercises at the end of each section. Each strategy is supported by illustrations, and the source code can be accessed by the link in file.
Optimisation methods. Theorems
This lecture note contains the main theorems and facts on optimization methods. The problem of convex optimization, which is often encountered in practice, is particularly widely disclosed. Convex optimization includes linear, quadratic, and semi-definite programming problems.