arXiv research

Physics-constrained deep learning predicts geophysical dynamics with boundedness.

Proposes r2SGLD for efficient constrained exploration in non-convex learning.

Proposes a Gaussian process model for constrained dynamics learning.

Extends Langevin dynamics for constrained domains.

Proposes a new method for constrained generative modeling using Langevin dynamics.

New algorithm improves convergence for non-convex problems with boundaries.

DE-PSGLD samples from constrained distributions in a decentralized manner.

The aim of this paper is to study the relationship between Hamiltonian dynamics and constrained variational calculus. We describe both using the notion of Lagrangian submanifolds of convenient symplectic manifolds and using the so-called Tulczyjew's triples. The results are also extended to the case of discrete dynamic…

PNDEs project neural dynamics onto constraint manifolds, improving accuracy and stability.

Solves VaR-constrained portfolio optimization in markets with stochastic volatility.

We show that there exists a natural Tulczyjew triple in the dynamics of objects for which the standard kinematic configuration space $TM$, i.e. the tangent bundle, is replaced with its $n$-th exterior power, i.e. the bundle of tangent $n$-vectors. In this framework, which is fully covariant, we geometrically derive pha…

This work accelerates constrained sampling using large deviation principles.

MAGI-X learns unknown dynamics from data without numerical integration.

Unified framework for constrained diffusion models on nonconvex sets with efficient landing mechanism.

KCRL learns stable policies for nonlinear systems with formal guarantees.

Paper introduces mcTangent for real-time dynamical systems.

New algorithms for sampling in constrained domains without learning rates.

Optimizes portfolios with constraints and stochastic factors, deriving explicit solutions.

In this paper, we study a constrained utility maximization problem following the convex duality approach. After formulating the primal and dual problems, we construct the necessary and sufficient conditions for both the primal and dual problems in terms of FBSDEs plus additional conditions. Such formulation then allows…

With the growth of renewable generation (RG) and the development of associated ride through curves serving as operating limits, during disturbances, on violation of these limits, the power system is at risk of losing large amounts of generation. In order to identify preventive control measures that avoid such scenarios…

New algorithm improves sampling from constrained spaces.

A new RL method handles uncertainty and constraints in real-time optimization.

The paper studies dynamical properties in semigroups modulo ideals.

New method learns nonlinear projections for reduced-order modeling of complex dynamical systems.

Safe RL in linear systems achieves $\sqrt{T}$-regret.

Optimal control problems on Riemannian manifolds are solved by penalizing constraint violations.

OLLA framework efficiently samples from constrained distributions with nonconvex constraints.

This paper presents a geometric description on Lie algebroids of Lagrangian systems subject to nonholonomic constraints. The Lie algebroid framework provides a natural generalization of classical tangent bundle geometry. We define the notion of nonholonomically constrained system, and characterize regularity conditions…

New algorithms improve sampling from constrained distributions.

DGNet solves complex dynamical systems with neural networks and constraints.

New algorithm samples constrained distributions efficiently.

Dynamic pricing learns demand model from sparse product networks.

Physics-constrained GP predicts material states under shockwave conditions.

New algorithms improve sampling from constrained distributions.

We study the structure of a simple dynamic optimization problem consisting of one state and one control variable, from a physicist's point of view. By using an analogy to a physical model, we study this system in the classical and quantum frameworks. Classically, the dynamic optimization problem is equivalent to a clas…

Study proposes adaptive RL for dynamic portfolio optimization.

We consider the problem of realizing tight contact structures on closed orientable three-manifolds. By applying the theorems of Hofer et al., one may deduce tightness from dynamical properties of (Reeb) flows transverse to the contact structure. We detail how two classical constructions, Dehn surgery and branched cover…

We consider an optimal stopping problem where a constraint is placed on the distribution of the stopping time. Reformulating the problem in terms of so-called measure-valued martingales allows us to transform the marginal constraint into an initial condition and view the problem as a stochastic control problem; we esta…

New algorithms for constrained online optimization with memory and predictions.

Koopman Regularization learns governing equations from sparse data.

We present a novel technique to solve the problem of managing optimally a pumped hydroelectric storage system. This technique relies on representing the system as a stochastic optimal control problem with state constraints, these latter corresponding to the finite volume of the reservoirs. Following the recent level-se…

We solve the problem of optimal stopping of a Brownian motion subject to the constraint that the stopping time's distribution is a given measure consisting of finitely-many atoms. In particular, we show that this problem can be converted to a finite sequence of state-constrained optimal control problems with additional…

The paper solves multi-period portfolio selection with constraints using a dynamic factor model.

Service-induced congestion in memory-constrained LLM serving

Develops adiabatic theory for ACW flow on surfaces.

End-to-end framework optimizes constrained trajectories using data-driven methods.

Machine learning infers time-reversible dynamics from data.

The Hawking energy is nonnegative and rigid on area-constrained surfaces in general relativity.