arXiv:2603.26923v1 Announce Type: cross
Abstract: Parametric models deployed in non-stationary environments degrade as the underlying data distribution evolves over time (a phenomenon known as temporal domain drift). In the current work, we present KO…
arXiv:2603.11066v4 Announce Type: replace-cross
Abstract: We develop a structural framework for the Collatz map based on odd-to-odd dynamics, modular return structure, and a decomposition of trajectories into bursts and gaps.
On the unconditional si…
arXiv:2603.11560v3 Announce Type: replace-cross
Abstract: This paper develops a dynamical framework for adaptive coordination in systems of interacting agents referred to here as Feedback-Coupled Memory Systems (FCMS). Instead of framing coordination …
arXiv:2502.01557v3 Announce Type: replace-cross
Abstract: Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules ca…
arXiv:2603.26464v1 Announce Type: new
Abstract: In this paper, we present a Koopman autoencoder-based least-squares policy iteration (KAE-LSPI) algorithm in reinforcement learning (RL). The KAE-LSPI algorithm is based on reformulating the so-called le…
arXiv:2603.20904v3 Announce Type: replace-cross
Abstract: The proposed algorithm seeks to provide a novel data-driven framework for the discovery of stochastic differential equations (SDEs) by application of the Weak-formulation to stochastic SINDy. T…
arXiv:2603.23854v1 Announce Type: new
Abstract: Symbolic discovery of governing equations is a long-standing goal in scientific machine learning, yet a fundamental trade-off persists between interpretability and scalable learning. Classical symbolic r…
arXiv:2603.14831v3 Announce Type: replace-cross
Abstract: We construct a cellular sheaf from any feedforward ReLU neural network by placing one vertex for each intermediate quantity in the forward pass and encoding each computational step – affine tra…
arXiv:2603.11066v3 Announce Type: replace-cross
Abstract: We develop a structural and quantitative framework for analyzing the Collatz map through modular dynamics, valuation statistics, and combinatorial decomposition of trajectories into bursts and …
arXiv:2509.19672v2 Announce Type: replace
Abstract: Stochastic optimal control methods often struggle in complex non-convex landscapes, frequently becoming trapped in local optima due to their inability to learn from historical trajectory data. This p…