Continuous‐time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations
From MaRDI portal
Publication:6196292
DOI10.1111/mafi.12422arXiv2202.06637OpenAlexW4389038502MaRDI QIDQ6196292
Justin A. Sirignano, Ziheng Wang
Publication date: 14 March 2024
Published in: Mathematical Finance (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2202.06637
stochastic differential equationsmachine learningPoisson equationsstochastic gradient descentonline optimization
Learning and adaptive systems in artificial intelligence (68T05) Optimal stochastic control (93E20) Applications of stochastic analysis (to PDEs, etc.) (60H30)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Incorporating order-flow into optimal execution
- A Fokker-Planck control framework for multidimensional stochastic processes
- Continuous-time stochastic control and optimization with financial applications
- On Poisson equation and diffusion approximation. II.
- Speculative futures trading under mean reversion
- Parameter estimation in SDEs via the Fokker-Planck equation: likelihood function and adjoint based gradient computation
- Optimal control of the Fokker-Planck equation with space-dependent controls
- Incorporating signals into optimal trading
- On the Poisson equation and diffusion approximation. I
- Online drift estimation for jump-diffusion processes
- Ergodic behavior of control and mean field games problems depending on acceleration
- Strong convergence order for slow-fast McKean-Vlasov stochastic differential equations
- Adaptive Euler-Maruyama method for SDEs with nonglobally Lipschitz drift
- Estimation of affine term structure models with spanned or unspanned stochastic volatility
- Mean field games and systemic risk
- Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement
- Ergodic Control of Diffusion Processes
- The Shape and Term Structure of the Index Option Smirk: Why Multifactor Stochastic Volatility Models Work So Well
- Adaptive continuous-time linear quadratic Gaussian control
- Gradient Convergence in Gradient methods with Errors
- Transform Analysis and Asset Pricing for Affine Jump-diffusions
- High-dimensional Hawkes processes for limit order books: modelling, empirical analysis and numerical calibration
- Stochastic Gradient Descent in Continuous Time
- MEAN REVERSION TRADING WITH SEQUENTIAL DEADLINES AND TRANSACTION COSTS
- Optimization Methods for Large-Scale Machine Learning
- Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games I: The Ergodic Case
- Numerical solution to 3D bilinear Fokker–Planck control problem
- State-dependent Hawkes processes and their application to limit order book modelling
- Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem
- Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
- Stochastic Processes and Applications
- Linear-Quadratic $N$-person and Mean-Field Games with Ergodic Cost
- Online Maximum-Likelihood Estimation of the Parameters of Partially Observed Diffusion Processes
- OPTIMAL MEAN REVERSION TRADING WITH TRANSACTION COSTS AND STOP-LOSS EXIT
- A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options
- Joint Online Parameter Estimation and Optimal Sensor Placement for the Partially Observed Stochastic Advection-Diffusion Equation
- Online parameter estimation for the McKean-Vlasov stochastic differential equation
