Stability and Convergence of Stochastic Approximation using the O.D.E. Method
, 1998 It is shown that the stability of the stochastic approximation algorithm is implied by the asymptotic stability of the origin for an associated ODE. This in turn implies convergence of the algorithm.
Meyn, SP, Borkar, VS
core
Few Shot Learning for Flame State Monitoring From Limited Visible and Infrared Images
Expert Systems, Volume 43, Issue 11, November 2026.ABSTRACT The success of machine learning in image‐based combustion monitoring requires big data, which is costly, and even impossible in industrial applications. To address this, we introduce metric‐based few shot learning for combustion monitoring and classification, to the best of our knowledge, for the first time.
Ruiyuan Kang +2 more
wiley +1 more source
Behavioural Diversity of Fishes: Concepts, Drivers and Its Role in Conservation and Management
Fish and Fisheries, Volume 27, Issue 6, Page 1245-1268, November 2026.ABSTRACT Human activity has altered nearly all ecosystems on Earth, contributing to substantial biodiversity loss across taxonomic, genetic and functional dimensions, from the intraspecific to the ecosystem scale. Yet some components of biodiversity remain hidden or underappreciated, including behavioural diversity.
Marie Prchalová +25 more
wiley +1 more source
Stochastic approximation with delayed updates: Asynchronous Machine Learning Algorithms study
International audienceIn this paper, we investigate the convergence dynamics of stochastic approximation algorithms under delayed gradient updates and their impact on asynchronous machine learning performance.
Nguyen, Hong Phuc +2 more
core
Exact BER Performance of Asynchronous MC-DS-CDMA over Fading Channels
, 2010 In this contribution an accurate average Bit Error Rate (BER) formula is derived for MC-DS-CDMA in the context of asynchronous transmissions and random spreading sequences. We consider a flat Nakagami-m fading channel for each subcarrier. Our analysis is
Smida, Besma +2 more
core +1 more source
Approximation of Jump Diffusions in Finance and Economics [PDF]
In finance and economics the key dynamics are often specified via stochastic differential equations (SDEs) of jump-diffusion type. The class of jump-diffusion SDEs that admits explicit solutions is rather limited.
Nicola Bruti-Liberati, Eckhard Platen
core
, 2007 Quadrature Amplitude Modulation (QAM) is a bandwidth-efficient transmission technique. The exact average Bit Error Ratio (BER) of the maximum-minimum-distance rectangular QAM (R-QAM) constellation is studied in the context of asynchronous Co-Channel ...
Liu, X., Hanzo, L.
core
Convergence of Batch Asynchronous Stochastic Approximation With Applications to Reinforcement Learning [PDF]
We begin by briefly surveying some results on the convergence of the Stochastic Gradient Descent (SGD) Method, proved in a companion paper by the present authors. These results are based on viewing SGD as a version of Stochastic Approximation (SA).
Vidyasagar, M., Karandikar, Rajeeva L.
core +1 more source
A general framework for statistical inference on discrete event systems. [PDF]
We present a framework for statistical analysis of discrete event systems which combines tools such as simulation of marked point processes, likelihood methods, kernel density estimation and stochastic approximation to enable statistical analysis of the ...
Koning, A.J., Nicolai, R.P.
core
Characterizing open-ended evolution through undecidability mechanisms in random Boolean networks. [PDF]
NPJ Syst Biol ApplLópez-Díaz AJ +3 more
europepmc +1 more source