This letter summarizes and proves the concept of bounded-input bounded-state (BIBS) stability for weight convergence of a broad family of in-parameter-linear nonlinear neural architectures as it generally applies to a broad family of incremental grad...
This note corrects some technical inaccuracies in a recently published paper on predefined-time convergence (Automatica 112 (2020) 108710) and discusses implementation issues of the presented control algorithm....
We present a novel method for convex unconstrained optimization that, without any modifications, ensures: (i) accelerated convergence rate for smooth objectives, (ii) standard convergence rate in the general (non-smooth) setting, and (iii) standard c...
We present first results of astrophysically relevant experiments where highly supersonic plasma jets are generated via conically convergent flows. The convergent flows are created by electrodynamic acceleration of plasma in a conical array of fine...
This article explores the convergence properties of an $SLIR^\text{T}R^\text{P}D$ endemic model, incorporating Dirac and Radon measures, alongside distributed delays to represent latency and temporary immunity. A class of delays is defined for both c...
Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood beyond empirical heuristics. This paper develops a novel theoretical framework for experience replay in modern...
Dec 5, 2019 · I couldn't find any substantial list of 'strange infinite convergent series' so I wanted to ask the MSE community for some. By strange, I mean infinite series/limits that converge when you would …
Jun 3, 2025 · The Technology Convergence Report 2025 offers leaders a strategic lens – the 3C Framework – to help them navigate the combinatorial innovation era.
Jan 21, 2025 · Innovation thrives on technology convergence, combination, and compounding. Mastering these forces can help tackle global challenges and shape the future of technology.
Modern cloud databases are shifting from converged architectures to storage disaggregation, enabling independent scaling and billing of compute and storage. However, cloud databases still rely on external, converged coordination services (e.g., ZooKe...
For classification problems, trained deep neural networks return probabilities of class memberships. In this work we study convergence of the learned probabilities to the true conditional class probabilities. More specifically we consider sparse deep...
This Note presents original rates of convergence for the deconvolution problem. We assume that both the estimated density and noise density are supersmooth and we compute the risk for two kinds of estimators....
In this article we develop convergence theory for a class of goal-oriented adaptive finite element algorithms for second order nonsymmetric linear elliptic equations. In particular, we establish contraction results for a method of this type for Diric...
The DANE algorithm is an approximate Newton method popularly used for communication-efficient distributed machine learning. Reasons for the interest in DANE include scalability and versatility. Convergence of DANE, however, can be tricky; its appeali...
A necessary and sufficient condition for the convergence of an infinite right product of matrices of the form | I B | A = | 0 C |, with (uniformly) contracting submatrices $C$, is proven....
Consider a reflected jump-diffusion on the positive half-line. Assume it is stochastically ordered. We apply the theory of Lyapunov functions and find explicit estimates for the rate of exponential convergence to the stationary distribution, as time...
The paper studies the rate of convergence of the weak Euler approximation for solutions to possibly completely degenerate SDEs driven by Levy processes, with Hoelder-continuous coefficients. It investigates the dependence of the rate on the regularit...