338 papers
This paper investigates continuous-time multi-armed bandits with random intervention times, providing explicit characterizations of the optimal Gittins index for arms evolving as Lévy processes and specific subclasses like spectrally negative Lévy processes and diffusion processes.
This paper bridges learning-to-communicate in multi-agent systems with decentralized stochastic control by formalizing the problem under a common-information framework, identifying quasi-classical information structures as a tractable subclass, and developing provable algorithms with quasi-polynomial complexity for such scenarios.
This paper proposes a unified co-optimization framework for utility-scale off-grid renewable power-to-hydrogen systems that coordinates heterogeneous electrolyzers and other resources to maximize hydrogen production while ensuring frequency security through a novel system-level response model and stage-wise transient constraints.
This paper proposes a tractable, infinite-dimensional framework for assessing the long-term environmental impact of long-memory processes, such as benthic algae blooms, by formulating the problem as a solvable extended Hamilton-Jacobi-Bellman system that incorporates model uncertainty and nonexponential discounting.
This paper proposes an alternating learning framework for cooperative multi-agent reinforcement learning under communication constraints, where a global agent observes only a subset of local agents, and proves that this approach converges to an approximate Nash equilibrium with improved sample complexity compared to methods operating on the full joint state space.
This paper proposes a successive difference-of-convex method that leverages Moreau envelopes and the progressive hedging algorithm to solve a class of challenging two-stage nonconvex nonsmooth stochastic conic programs by reformulating them as nonmonotone nonsmooth stochastic variational inequalities, with theoretical convergence guarantees and numerical validation via an extended Markowitz model.
This paper proposes a convergent Plug-and-Play blind super-resolution framework that enhances clinical 1.5 T MRI images for improved multiple sclerosis diagnosis by jointly estimating high-resolution structures and unknown blur kernels without requiring prior degradation models.
This paper proposes a new ensemble filtering approach that inherently localizes the analysis probability density function via variational Bayesian optimization and marginal partitioning, thereby eliminating the need for ad-hoc localization techniques while achieving accuracy and computational efficiency comparable to tuned standard EnKF and ETKF methods.
This paper proposes an implicit-explicit trust region method that leverages the specific Hessian structure of Landau-type free energy functionals to efficiently compute second-order stationary points, enabling the identification of physically stable phases like the FDDD structure in the Landau-Brazovskii model with provable convergence guarantees.
This paper proposes a method to identify nonlinear acyclic networks in continuous time with nonzero initial conditions and full excitations, demonstrating that measuring all sinks is necessary and sufficient for identifying trees and general directed acyclic graphs, while utilizing higher-order derivatives and dictionary functions to recover edge dynamics and parallel paths.
This paper proposes a robust adaptive reformulation of an entropy-inspired KKT-based convergence indicator, utilizing quantile normalization to effectively assess stationarity in multi-objective optimization without relying on external reference sets.
This paper investigates the relative impact of inventory replenishment policies versus real-time online fulfillment algorithms on system profit under demand uncertainty, demonstrating that cumulative regret remains stable over long cycles and introducing a novel look-ahead algorithm that outperforms myopic baselines while identifying specific regimes where optimizing one lever yields greater revenue gains than the other.
This paper introduces a Riemannian gradient method with momentum that extends a recent unconstrained optimization technique, proving an worst-case complexity bound for finding -stationary points and demonstrating competitive performance against state-of-the-art solvers through extensive numerical experiments.
This paper investigates the Wasserstein gradient flow of semi-discrete energies relevant to urban planning and uniform quantization by proving the convergence of the JKO scheme to a singularly coupled PDE-ODE system, analyzing its qualitative properties such as atomic convergence to Laguerre cell barycenters, and validating these findings through numerical simulations that reveal dynamic crystallization phenomena.
This paper establishes a rigorous Lyapunov stability framework for a stochastic drift-diffusion model in multi-objective optimization and provides a reproducible Python implementation, demonstrating that while the method may underperform in low-dimensional settings, it offers a mathematically tractable and viable alternative for high-dimensional problems with restricted evaluation budgets.
This paper establishes a converse Lyapunov theorem for the boundedness of reachability sets in infinite-dimensional systems with Lipschitz continuous flows, demonstrating its applicability to semi-linear evolution equations and deriving a result for forward completeness in ordinary differential equations without restricting input magnitudes.
This paper demonstrates that while pure optimal strategies exist in infinite-horizon Markov decision processes with finite state and action spaces under diffuse charges satisfying the time value of money principle, optimal strategies (neither pure nor randomized) may fail to exist entirely if the aggregation charge is constructed without such assumptions.
This paper proposes a POMDP-based framework for optimizing maintenance in a two-component system with mixed observability and unidirectional degradation dependence, establishing structural policy properties, developing a Baum-Welch parameter estimation method, and demonstrating through numerical experiments that the approach outperforms classical threshold policies with cost reductions of up to 6%.