arXiv research

New KSDs control moments in approximations, improving diagnostics and tests.

The abstract discusses convergent realizations of Lie subalgebras in control theory.

The paper analyzes deep neural networks using control theory to set a time limit for their convergence.

Paper proves deep learning method for stochastic control converges and outperforms existing algorithms.

For Bezier curves, subdivision algorithms create control polygons as piecewise linear (PL) approximations that converge in terms of Hausdorff distance. We prove that the exterior angles of control polygons under subdivision converge to 0 at the rate of $O(\sqrt{\frac{1}{2^i}})$, where $i$ is the number of subdivisions.…

Method predicts hardware resource usage by control software with guaranteed linear convergence.

Variational inference is increasingly being addressed with stochastic optimization. In this setting, the gradient's variance plays a crucial role in the optimization procedure, since high variance gradients lead to poor convergence. A popular approach used to reduce gradient's variance involves the use of control varia…

Paper studies central bank's strategy to control systemic risk in interbank system.

Paper revisits set membership estimation for linear systems with relaxed disturbance bounds.

Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets, and we propose an actor-critic reinforcement learning algorithm that provably converges t…

Optimizes deep learning training by treating it as an optimal control problem.

Deep learning method proves convergence for high-dimensional PDEs.

We consider a new form of reinforcement learning (RL) that is based on opportunities to directly learn the optimal control policy and a general Markov decision process (MDP) framework devised to support these opportunities. Derivations of general classes of our control-based RL methods are presented, together with form…

New conditions ensure MMDs separate and converge to target distributions.

Develops neural network framework for risk-reward optimization problems.

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic…

Survey of theoretical foundations for policy optimization in control.

Adaptive optimal control of nonlinear dynamic systems with deterministic and known dynamics under a known undiscounted infinite-horizon cost function is investigated. Policy iteration scheme initiated using a stabilizing initial control is analyzed in solving the problem. The convergence of the iterations and the optim…

Paper introduces a new convergence for Lorentzian spaces using causal diamonds.

In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for continuous-time systems, policy iteration based QL (PIQL) and value iteration based…

Study controlled contagion with state-dependent killing, proving a comparison principle.

New deep learning method solves stochastic control problems.

Study on games with degenerate diffusion matrices, proving value existence and convergence.

The paper analyzes convergence of neural SDEs as sample size increases.

Study on PG learning for LQ MFC problems with common noise, proving convergence and sample complexity.

Robust $Q$-learning for mean-field control under Wasserstein uncertainty

The paper examines convergence of distances in Lipschitz structures on manifolds.

Paper uses Koopman operator and Nyström method for efficient nonlinear control.

The study analyzes momentum-based optimization algorithms from dynamical systems perspective.

Controlled interacting particle systems such as the ensemble Kalman filter (EnKF) and the feedback particle filter (FPF) are numerical algorithms to approximate the solution of the nonlinear filtering problem in continuous time. The distinguishing feature of these algorithms is that the Bayesian update step is implemen…

In this paper we prove a convergence result for sequences of Willmore immersions with simple minimal bubbles. To this end we replace the total curvature control in T. Rivière's proof of the $\varepsilon$-regularity for Willmore immersions by a control of the local Willmore energy.

GEORCE computes geodesics quickly and accurately.

EControl improves fast distributed optimization with compression and error control.

This paper improves Adam's performance in machine learning tasks.

Policy gradients methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a parameterized class of polices. Unfortunately, even for simple control problems solvable by standard dynamic programming techniques, policy gradient algorithms face non-convex optimization pro…

A new family of momentum coefficients improves the convergence rate of accelerated algorithms.

Study shows how to learn optimal policies quickly in stochastic control problems.

The paper analyzes reg-SGD for convex problems, proving convergence and quantifying the rate of convergence.

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all recent work in this area, we consider multiplicative noise models, which are increas…

Study on natural actor-critic for POMDPs with finite memory.

In this paper, we present a novel penalty approach for the numerical solution of continuously controlled HJB equations and HJB obstacle problems. Our results include estimates of the penalisation error for a class of penalty terms, and we show that variations of Newton's method can be used to obtain globally convergent…

Optimizes MCMC chains with neural control variates.

This work studies the contraction coefficients of Schrödinger bridge problems in linear systems.

BBVI with STL converges geometrically under perfect specification, with quadratic variance bound.

This paper develops numerical methods for finding optimal dividend pay-out and reinsurance policies. A generalized singular control formulation of surplus and discounted payoff function are introduced, where the surplus is modeled by a regime-switching process subject to both regular and singular controls. To approxima…

Paper studies constrained control games with a novel approximation method.

Deep Galerkin Method estimates value function for mean-field control problem.

The paper tackles learning to control systems with unknown parameters using Brownian noise.