New method uses backward SDEs for deep learning uncertainty.
problem Uncertainty quantification in deep learning models.
method Probabilistic machine learning with stochastic neural networks and stochastic optimal control.
result Effectiveness validated through numerical experiments.
NOVAS uses adaptive stochastic search for non-convex optimization in deep networks.
problem Non-convex optimization challenges in deep neural networks.
method Adaptive stochastic search for non-convex optimization.
result NOVAS outperforms existing alternatives in a structured prediction task.
Deep learning solves complex stochastic control with jumps.
problem Solving high-dimensional stochastic control tasks with jumps.
method Model-based approach using two neural networks, iteratively trained with objectives derived from the Hamilton-Jacobi-Bellman equation.
result Demonstrates effectiveness in solving complex high-dimensional stochastic control tasks.
A new ML algorithm solves complex economic control problems.
problem Solving high-dimensional, finite-horizon stochastic control problems in economics.
method Deep neural network representation of optimal policy functions with three key features.
result Efficiently solves various economic control problems including recursive utility and growth models.
Deep neural networks solve stochastic control problems with delay.
problem Challenges in stochastic control problems with delay due to path-dependence and high dimensions.
method Employing recurrent neural networks (RNNs) to parameterize policies and optimize objectives.
result RNNs, especially LSTMs, efficiently capture path-dependence and outperform feedforward networks in training and performance.
Paper introduces solving financial problems using time-stepped FBSDE and deep learning.
problem Quantitative finance problems under specific dynamics and instruments.
method Formulate as FBSDE, turn into control problems, time-step, solve with optimization and deep learning.
result Solves financial problems with new methods and deep learning.
New method reduces variance in complex probabilistic model optimization.
problem High variance in stochastic optimisation of complex models.
method Use recognition network to approximate optimal control variate for each mini-batch.
result Sub-optimal variance reduction is improved with new approach.
Deep Hedging learns optimal strategies for various risk levels.
problem Finding optimal hedging policies for diverse risk aversions.
method Continuous Reinforcement Learning with actor-critic algorithm.
result Demonstrated effectiveness in a stochastic volatility model.
Many real world stochastic control problems suffer from the "curse of dimensionality". To overcome this difficulty, we develop a deep learning approach that directly solves high-dimensional stochastic control problems based on Monte-Carlo sampling. We approximate the time-dependent controls as feedforward neural networ…
Extends DGM to solve PDEs and HJB equations in optimal control.
problem Solving PDEs and HJB equations in optimal control problems.
method Reparameterization and neural networks for positivity and normalization. Novel importance sampling for integral terms. Alternating stochastic gradient descent for simultaneous optimization.
result Solves PDEs and HJB equations in their primal form.
Deep RL improves power control and scheduling for wireless multicast systems.
problem Scalable power control and scheduling for wireless multicast networks.
method Deep reinforcement learning with function approximation using a deep neural network.
result Deep RL can learn optimal power control policies for large systems.
Paper optimizes aquaculture feeding and harvesting strategies for profit maximization.
problem Maximizing farm profit through optimal feeding and harvesting decisions under stochastic price dynamics.
method Developed a simplified aquaculture model and two numerical solution approaches: finite difference scheme and PINN-based method combined with DeepOS algorithm.
result PINN-based method achieves comparable accuracy to finite differences but is more scalable.
We present a deep recurrent neural network architecture to solve a class of stochastic optimal control problems described by fully nonlinear Hamilton Jacobi Bellmanpartial differential equations. Such PDEs arise when one considers stochastic dynamics characterized by uncertainties that are additive and control multipli…
Paper introduces multitask neural networks for efficient stochastic control problems.
problem Infeasibility of simulating state variables in some stochastic control problems.
method Multitask neural networks with dynamic task balancing.
result Multitask neural networks outperform state-of-the-art approaches in derivatives pricing problems.
Langevin algorithms enhance training of deep neural networks for stochastic control problems.
problem Training acceleration for deep neural networks in stochastic control problems.
method Application of Langevin algorithms to minimize the loss of deep neural networks in stochastic control problems.
result Langevin algorithms improve training on various stochastic control problems.
The paper bridges stochastic control and deep hedging for European call options with transaction costs.
problem Hedging and pricing European call options with proportional transaction costs.
method Complementary perspectives: stochastic control and deep hedging. Two architectures proposed: NTBN-Delta and WW-NTBN.
result WW-NTBN converges faster, matches no-transaction bands more closely, and generalizes well across transaction cost regimes.
Efficient deep policy gradient method for continuous-time control problems.
problem Optimal control in continuous time with fine time discretization.
method Multi-scale deep policy gradient method with varying time discretization.
result Targeted efficiency in computational resources achieved through multi-scale approach.
Paper presents deep LSMC method for efficient variable annuity pricing.
problem Efficiently pricing variable annuities with guarantees using simulation methods.
method Modifies least-squares Monte Carlo (LSMC) algorithm for optimal stochastic control problems.
result Deep LSMC provides more stable and robust pricing performance for higher-dimensional problems.
Deep neural RDEs improve portfolio optimization accuracy and risk sensitivity.
problem High-dimensional, path-dependent valuation and control problems.
method Coupling truncated log-signatures with a neural RDE backbone.
result Improved accuracy, tail fidelity, and training stability across various financial models.
Paper proves deep learning method for stochastic control converges and outperforms existing algorithms.
problem Formulating and solving stochastic control problems using FBSDE and SMP.
method Deep learning algorithm based on SMP, with convergence proof and error bounds.
result Deep SMP-BSDE algorithm converges and outperforms existing methods in high-dimensional stochastic control problems.
DQNs can approximate optimal Q-functions with high accuracy on compact sets.
problem Approximating optimal Q-functions in continuous-time Markov Decision Processes.
method Stochastic control, FBSDEs, residual network approximation theorems, large deviation bounds, viscosity solutions.
result DQNs can approximate optimal Q-functions on compact sets with arbitrary accuracy and high probability.
Attempts from different disciplines to provide a fundamental understanding of deep learning have advanced rapidly in recent years, yet a unified framework remains relatively limited. In this article, we provide one possible way to align existing branches of deep learning theory through the lens of dynamical system and …
DNN policies improve stochastic AC OPF for power grid optimization.
problem Optimizing power grid operations under uncertainty.
method Deep neural network (DNN) policies for real-time generator dispatch decisions.
result DNN policies enforce feasibility constraints and produce near optimal solutions.
New method solves stochastic control problems with delays using deep learning.
problem Stochastic control problems with delayed control in drift and diffusion.
method Characterization via Riccati PDEs and deep learning scheme.
result Illustrates effect of delay on Markowitz portfolio allocation problem.
Two deep learning algorithms solve utility maximisation problems in finance.
problem Solving utility maximisation problems in finance with deep learning.
method Two algorithms: one for Markovian problems via HJB equation and 2BSDE, the other for non-Markovian problems via adjoint BSDE.
result Highly accurate results with low computational cost, solving problems with power, log, and non-HARA utilities in various models.
Deep neural nets solve complex insurance math equations.
problem Optimal control problems in insurance math.
method Deep neural network algorithm for elliptic PDEs.
result Solves high-dimensional semilinear elliptic PDEs.
New deep learning method solves stochastic control problems.
problem Solving strongly coupled FBSDEs for stochastic control.
method Modified deep BSDE method with new loss function.
result Empirical convergence of the new method for three problems.
RL and DTSOC for final quadratic hedging performance studied.
problem Optimal hedging of European call options with and without transaction costs.
method Reinforcement Learning and Deep Trajectory-based Stochastic Optimal Control.
result RL and DTSOC perform similarly to variance-optimal hedging in various market models.
This paper develops algorithms for high-dimensional stochastic control problems based on deep learning and dynamic programming. Unlike classical approximate dynamic programming approaches, we first approximate the optimal policy by means of neural networks in the spirit of deep reinforcement learning, and then the valu…
Abstract: Surveying connections between ML and Control Theory.
problem Addressing the intersection of Machine Learning and Control Theory.
method Develops connections through reinforcement learning, supervised learning, deep learning, and stochastic gradient descent.
result Machine Learning and Control Theory are interconnected, with ML solving large control problems and Control Theory providing tools for ML.
Deep RL controller outperforms market making benchmarks in a Hawkes process model.
problem Optimal market making in financial markets.
method Deep reinforcement learning on a Hawkes process-based simulator.
result Deep RL controller outperforms benchmarks in various risk-reward metrics.
Develops a framework for analyzing neural networks and ODE models using control theory.
problem Analyzing deep neural networks and neural ODE models trained with stochastic gradient algorithms.
method Identifies connections between control theory, deep learning, and statistical sampling; derives Pontryagin's optimality principle and Mean-Field Langevin dynamics.
result Derives explicit convergence rates and provides quantitive bounds on generalization error, showing dimension-independent rates.
Study portfolio optimization with partial info and drawdown constraints using deep learning.
problem Optimizing portfolios with partial information and maximum drawdown constraints.
method Bayesian framework, dynamic programming, semi-explicit solutions, deep learning for stochastic control.
result Numerical solutions and performance analysis with deep learning, convergence to Merton problem.
Study robust control for systems with continuous states using adversarial perturbations.
problem Fragile policies in Markov control models under internal or external perturbations.
method Distributionally robust stochastic control with adaptive adversarial perturbations.
result Optimal robust policies for continuous state systems with uniform learning guarantees.
Deep learning improves optimal trading strategies in complex markets.
problem Finding optimal trading strategies in markets with multiple time scales.
method Deep differentiable reinforcement learning applied to optimal trading.
result Deep learning leads to more accurate and stable optimal trading strategies.
Study compares RL and DT-based control for hedging European call options.
problem Optimizing hedging strategies for European call options with transaction costs.
method Reinforcement Learning vs. Deep Trajectory-based Stochastic Control.
result RL and DT-based methods perform differently under stepwise mean-variance hedging.
Derives optimal control conditions using calculus of variations.
problem Optimizing Markov control in stochastic control problems.
method Calculus of variations approach to derive necessary conditions.
result Solves the Merton portfolio optimization problem.
Algorithm optimizes system design and control for better rewards.
problem Optimizing system design and control for maximum rewards.
method Deep reinforcement learning combining policy gradient and model-based optimization.
result DEPS algorithm outperforms state-of-the-art methods in various environments.
The challenge in controlling stochastic systems in which low-probability events can set the system on catastrophic trajectories is to develop a robust ability to respond to such events without significantly compromising the optimality of the baseline control policy. This paper presents CelluDose, a stochastic simulatio…
Optimizes MCMC chains with neural control variates.
problem Reducing variance in Markov Chain Monte Carlo (MCMC) simulations.
method Uses neural networks as control variates to minimize asymptotic variance.
result Derives optimal convergence rate under various ergodicity assumptions.
The paper analyzes convergence of neural SDEs as sample size increases.
problem Understanding the limiting behavior of neural SDEs as sample size grows.
method Analyzes Hamilton-Jacobi-Bellman equation and uses stochastic maximum principle.
result Convergence of minima and optimal parameters of neural SDEs as sample size increases.
Study proves optimal controls for stochastic Volterra equations with singular kernels.
problem Existence of optimal controls for stochastic Volterra equations with singular kernels.
method Sufficient conditions based on integrability and growth hypotheses.
result Existence of optimal relaxed and strict controls under classical convexity assumptions.
Optimizes control of infectious disease spread using stochastic methods.
problem Optimizing control of highly infectious diseases like COVID-19.
method Reformulated Hamilton-Jacobi-Bellman equation as stochastic minimum principle, leading to forward-backward stochastic differential equations.
result Numerous numerical solutions presented under various scenarios.
NOVI improves deep Gaussian process inference with neural generators and regularized Stein discrepancy.
problem Intractable exact inference in deep Gaussian processes.
method NOVI uses a neural generator to approximate the posterior distribution and minimizes Regularized Stein Discrepancy.
result NOVI achieves 93.56% classification accuracy on CIFAR10, outperforming state-of-the-art methods.
A new method for stochastic optimal control improves accuracy over existing techniques.
problem Improving the accuracy of stochastic optimal control for noisy systems.
method Stochastic Optimal Control Matching (SOCM) using Iterative Diffusion Optimization (IDO) with path-wise reparameterization trick.
result SOCM achieves lower error than existing techniques for three out of four control problems, sometimes by an order of magnitude.
This paper presents a novel approach to numerically solve stochastic differential games for nonlinear systems. The proposed approach relies on the nonlinear Feynman-Kac theorem that establishes a connection between parabolic deterministic partial differential equations and forward-backward stochastic differential equat…
Market makers and exchanges use deep reinforcement learning to optimize fees and trading flows.
problem Optimizing fees and trading flows in a lit and dark pool market.
method Solve stochastic control problem, derive optimal contract, design deep reinforcement learning algorithms.
result Deep reinforcement learning algorithms approximate optimal controls and incentives.
Constraints improve deep neural network training by stabilizing and enhancing robustness.
problem Vanishing/exploding gradients and poor weight magnitudes in deep neural networks.
method Weight-constrained stochastic dynamics using Langevin dynamics framework.
result Enhanced exploration of the loss landscape and improved generalization.