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 …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Optimal Control Theory”
Survey of theoretical foundations for policy optimization in control.
problem Understanding the theoretical properties of gradient-based methods in control and reinforcement learning.
method Interdisciplinary review of optimization landscape, convergence, and sample complexity for various control problems.
result Recent theoretical results on stability and robustness in learning-based control.
Optimizes electric field to control molecule states in Hartree-Fock theory.
problem Optimizing electric field to drive molecule from initial to target state.
method Trust region optimization with gradients from adjoint state method.
result Achieves desired target states with minimal control effort.
Study of 2D Lorentzian anti-de Sitter plane using geometric control theory.
problem Understanding extremal trajectories and reachable set on anti-de Sitter plane.
method Geometric control theory and differential geometry.
result Construction of optimal synthesis and description of Lorentzian distance.
Optimal control theory connects diffusion models to generative modeling.
problem Sampling from unnormalized densities in statistics and computational sciences.
method Deriving a Hamilton-Jacobi-Bellman equation and applying control theory to minimize Kullback-Leibler divergence.
result Time-reversed diffusion sampler (DIS) outperforms other diffusion-based sampling methods.
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.
Optimal Control Theory optimizes neural networks, improving robustness and efficiency.
problem Optimizing deep neural networks (DNNs) for better performance and efficiency.
method Integrating Optimal Control Theory with Backpropagation to develop a new optimizer.
result Optimal Control Theoretic Neural Optimizer (OCNOpt) improves upon existing methods in robustness and efficiency.
A general study of symmetries in optimal control theory is given, starting from the presymplectic description of this kind of system. Then, Noether's theorem, as well as the corresponding reduction procedure (based on the application of the Marsden-Weinstein theorem adapted to the presymplectic case) are stated both in…
New control theory for self-path-dependent problems solves unique constraints.
problem Optimal control with self-path-dependent constraints in stochastic systems.
method Introduces new HJB equations for variational inequalities with historical maximum controls.
result Value functions are viscosity solutions to HJB equations under Lipschitz conditions.
Motivated by the ubiquity of control-affine systems in optimal control theory, we investigate the geometry of point-affine control systems with metric structures in dimensions two and three. We compute local isometric invariants for point-affine distributions of constant type with metric structures for systems with 2 s…
Gradient descent on LSE objectives implicitly performs EM, leading to collapse without volume control.
problem Gradient collapse in autoencoders without volume control.
method Introduced a single-layer encoder with an LSE objective and InfoMax regularization for volume control.
result Gradient--responsibility identity holds exactly; LSE alone collapses; variance prevents dead components; decorrelation prevents redundancy.
Non-bilinear observations make optimal control harder, showing non-convex costs and non-affine optimal controllers.
problem Optimal control from bilinear observations in linear systems is challenging.
method Analytical and numerical methods to study the non-convex cost-to-go and non-affine optimal controllers.
result The Separation Principle does not hold for bilinear observations, leading to non-convex costs and non-affine optimal controllers.
Learning-Based Optimal Control with Performance Guarantees for Unknown Systems with Latent Stateseess.SY
Paper proposes method for optimal control of unknown systems with latent states.
problem Jointly estimating dynamics and latent states in systems with unmeasurable states.
method Combination of particle Markov chain Monte Carlo methods and scenario theory.
result Probabilistic performance guarantees for optimal input trajectories.
Nonsmooth High-Order Averaging Theory with Application to Extremum Seeking Optimization and Controlmath.OC
New theory for nonsmooth systems helps optimize and control complex functions.
problem Optimizing and controlling systems with nonsmooth functions.
method Higher-order averaging theory with nonsmooth near-identity transformation and lexicographic differentiation.
result Closed formula for nonsmooth first and second-order averaging.
The paper tackles Neyman-Pearson classification control issues.
problem Neyman-Pearson classification's control constraint is hard to satisfy in finite samples.
method Developed refined learning procedures under two accuracy control strategies.
result Proposed methods achieve desired control levels in finite samples.
We review some recent results on the theory of Lagrangian systems on Lie algebroids. In particular we consider the symplectic and variational formalism and we study reduction. Finally we also consider optimal control systems on Lie algebroids and we show how to reduce Pontryagin maximum principle.
I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, includi…
Turnpike property applies to optimal control of PDEs and ResNets.
problem Optimal control of PDEs and ResNets.
method Mathematical formalization and controllability analysis.
result Optimal controls and states are nearly constant over most of the time.
Online Optimization and Ambiguity-based Learning of Distributionally Uncertain Dynamic Systemseess.SY
Paper proposes online optimization for uncertain systems using machine learning and DRO.
problem Optimization of uncertain dynamical systems with distributional uncertainty.
method Combines machine learning with Distributional Robust Optimization (DRO) to handle uncertainty.
result Online solutions with probabilistic regret bounds for uncertain systems.
The paper presents the geometry of Lie algebroids and its applications to optimal control. The first part deals with the theory of Lie algebroids, connections on Lie algebroids and dynamical systems defined on Lie algebroids (mainly Lagrangian and Hamiltonian systems). In the second part we use the framework of Lie alg…
New method uses neural networks to solve complex PDEs from optimal control theory.
problem Solving high-dimensional Hamilton-Jacobi-Bellman PDEs.
method Iterative diffusion optimization techniques, focusing on path measures and divergences.
result Favourable properties of log-variance divergence for Monte Carlo estimators.
Portfolio optimization for a large investor controlling market sentiment under partial informationq-fin.MF
We consider an investor faced with the utility maximization problem in which the risky asset price process has pure-jump dynamics affected by an unobservable continuous-time finite-state Markov chain, the intensity of which can also be controlled by actions of the investor. Using the classical filtering theory, we redu…
Unified approach to stochastic control, filtering, and stopping using rough paths.
problem Addressing gaps in classical problems of stochastic control, filtering, and stopping.
method Combining rough path theory with controlled rough paths to provide a pathwise deterministic framework.
result Established rigorous connection between candidate solutions and Hamilton-Jacobi-Bellman equation.
New algorithm controls systems with unknown, changing losses.
problem Control systems with adversarial perturbations and unknown loss function.
method Efficient sublinear regret algorithm for bandit convex optimization with memory.
result Achieves efficient control with sublinear regret in the presence of unknown, changing losses.
Study optimal control in unknown nonlinear systems with near-optimal regret bound.
problem Sequential control in unknown, nonlinear dynamical systems.
method LC^3 algorithm, based on information theory.
result Near-optimal regret bound for episodic settings.
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 proves index theorems for graph-based optimal control problems.
problem Optimal control problems on graphs with constraints.
method Proves Morse index theorems for a broad class of variational problems on graphs.
result Formulas compute the difference of Hessians related to different graphs or boundary conditions.
Sub-Finsler structures from the time-optimal control viewpoint for some nilpotent distributionsmath.DG
In this paper we study the sub-Finsler geometry as a time-optimal control problem. In particular, we consider non-smooth and non-strictly convex sub-Finsler structures associated with the Heisenberg, Grushin, and Martinet distributions. Motivated by problems in geometric group theory, we characterize extremal curves, d…
Modeling financial systemic risk with optimal control theory for stability.
problem Analyzing and stabilizing systemic risk in interconnected financial entities.
method Developed a theoretical model using optimal control theory, including steps for synthesizing stabilizing controllers.
result The model ensures that the norms of the mappings from disturbance to output are less than a predefined constant, stabilizing the system.
This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown. We propose a multi-stage procedure, called Coarse-ID control, that estimates a model from a few experimental trials, estimates the error in that model with respect to the truth, and then d…
An optimal control problem associated with the dynamics of the orientation of a bipolar molecule in the plane can be understood by means of tools in differential geometry. For first time in the literature -symplectic formalism is used to provide the optimal control problems associated to some families of partial dif…
We give the simple proof of Bobkov's inequality using the arguments of dynamical programming principle. As a byproduct of the method we obtain a characterization of optimizers.
A new depth measure based on optimal control theory captures multi-modal data.
problem Statistical depths for high-dimensional data.
method Eikonal equations and optimal control theory.
result The new depth measure is robust under adversarial models.
The paper solves a consumption-investment problem with state-dependent lower bounds.
problem A life-time consumption-investment problem with a state-dependent lower bound on consumption.
method Transformed the problem into a state-independent control problem to apply standard theory.
result Explicit optimal strategies provided for both homogeneous and non-homogeneous constraints.
The paper solves a complex control problem with stochastic elements and switching conditions.
problem Non-homogeneous stochastic LQ control with regime switching and random coefficients.
method Explicit optimal control and value obtained through two systems of backward stochastic differential equations (BSDEs). Existence and uniqueness of solutions proved using BMO martingales and contraction mapping method.
result Explicit optimal state feedback control and optimal value derived for the problem.
This manuscript surveys reinforcement learning from the perspective of optimization and control with a focus on continuous control applications. It surveys the general formulation, terminology, and typical experimental implementations of reinforcement learning and reviews competing solution paradigms. In order to compa…
We develop a general theory of convex duality for certain singular control problems, taking the abstract results by Kramkov and Schachermayer (1999) for optimal expected utility from nonnegative random variables to the level of optimal expected utility from increasing, adapted controls. The main contributions are the f…
Control of drawdown, that is, the control of the drops in wealth over time from peaks to subsequent lows, is of great concern from a risk management perspective. With this motivation in mind, the focal point of this paper is to address the drawdown issue in a stock trading context. Although our analysis can be carried …
Optimizes costs in uncertain Markov systems using risk filters.
problem Optimizing costs in systems with model uncertainty and unknown parameters.
method Risk filters and Bellman principle of optimality applied to Bayesian framework.
result Derives the Bellman principle for non-standard risk-averse control problems.
Solves inventory control with unknown demand trend using singular control.
problem Optimally managing inventory with an unknown demand trend.
method Formulates as a stochastic control problem under partial observation, solves equivalent separated problem using transition between formulations, and applies viscosity theory.
result Constructs an optimal control rule and shows bounded Lipschitz continuity of free boundaries.
Agents acting in the natural world aim at selecting appropriate actions based on noisy and partial sensory observations. Many behaviors leading to decision mak- ing and action selection in a closed loop setting are naturally phrased within a control theoretic framework. Within the framework of optimal Control Theory, o…
GT-DDP optimizer trains residual networks using game theory.
problem Applying DDP to residual networks.
method Game-theoretic DDP optimizer for residual networks.
result Improved training convergence and variance reduction.
New control theory shows neural networks can be sparsely active over time.
problem Optimizing neural networks for long-time control with sparsity constraints.
method Proving optimal controls vanish after a positive time and providing a stability estimate.
result Optimal controls for -penalized neural ODEs are sparsely active over time.
Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system's dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative calculations. We present a novel neurobiologically inspired hierarchical learning framework, Reinfor…
Optimizes exploration for nonlinear systems to learn controllers efficiently.
problem Learning optimal controllers for unknown nonlinear systems.
method Formally quantifies which parameters are most critical, and develops an algorithm to efficiently explore these parameters.
result Proves a near-instance-optimal rate for learning controllers.
Improves generalization in learning problems with small parameter method.
problem Improving generalization in learning problems with high-dimensional nonlinear functions.
method Perturbation theory applied to a weakly-controlled gradient system.
result Approximate optimal solutions for improving generalization with small noise.
Study of multidimensional control problems with reflection controls.
problem Solving control problems with reflection controls in multidimensional settings.
method Gradient descent algorithm for polytope approximations, data-driven domain estimator, episodic learning algorithm.
result Data-driven solutions for unknown diffusion dynamics with sublinear regret.
Pronounced variability due to the growth of renewable energy sources, flexible loads, and distributed generation is challenging residential distribution systems. This context, motivates well fast, efficient, and robust reactive power control. Real-time optimal reactive power control is possible in theory by solving a n…