Results 31 to 40 of about 307,922 (236)
Asymptotic Convergence of Thompson Sampling
Thompson sampling has been shown to be an effective policy across a variety of online learning tasks. Many works have analyzed the finite time performance of Thompson sampling, and proved that it achieves a sub-linear regret under a broad range of probabilistic settings. However its asymptotic behavior remains mostly underexplored.
Kalkanli, Cem, Ozgur, Ayfer
openaire +2 more sources
This work reports a direct, biocompatible method to synthesize UiO‐66, enabling one‐step encapsulation of proteins without compromising crystallinity or activity. Using advanced in situ and ex situ techniques, the study reveals that proteins integrate concurrently with MOF growth, forming crystalline protein@UiO‐66 nanoparticles, and provide insight ...
Jesús Cases Díaz +5 more
wiley +1 more source
Excess-Risk of Distributed Stochastic Learners
This work studies the learning ability of consensus and diffusion distributed learners from continuous streams of data arising from different but related statistical distributions. Four distinctive features for diffusion learners are revealed in relation
Chen, Jianshu +2 more
core +1 more source
Convergence rates in precise asymptotics
Let \(X,X_1,X_2,\ldots\) be i.i.d. random variables with partial sums \(S_n=\sum_{k=1}^nX_k\). Suppose that \(\operatorname{E}[X]=0\) and \(\operatorname{E}[X^2]=\sigma^2\in(0,\infty)\), then \textit{C. C. Heyde}'s result [J. Appl. Probab. 12, 173--175 (1975; Zbl 0305.60008)] on precise asymptotics states that \[ \lim_{\varepsilon\downarrow0 ...
Gut, Allan, Steinebach, Josef
openaire +1 more source
This work establishes a framework for high‐resolution printed interconnects by coupling e‐jet printing control, multilayer deposition, and sintering optimization. Ink properties and printing speed influence particle stacking, while different sintering atmospheres drive distinct microstructural evolution.
Kaifan Yue +6 more
wiley +1 more source
This study explores how information processing is distributed between brains and bodies through a codesign approach. Using the “backpropagation through soft body” framework, brain–body coupling agents are developed and analyzed across several tasks in which output is generated through the agents’ physical dynamics.
Hiroki Tomioka +3 more
wiley +1 more source
Linearizing and Forecasting: A Reservoir Computing Route to Digital Twins of the Brain
A new approach uses simple neural networks to create digital twins of brain activity, capturing how different patterns unfold over time. The method generates and recovers key dynamics even from noisy data. When applied to fMRI, it predicts brain signals and reveals distinctive activity patterns across regions and individuals, opening possibilities for ...
Gabriele Di Antonio +3 more
wiley +1 more source
We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in ...
Bhatnagar, Shalabh, Karmakar, Prasenjit
core +1 more source
Human‐relevant methods are essential for modern chemical safety assessment. This study helps define the capabilities and boundaries of an in vitro testing battery for developmental neurotoxicity by exploring its biological applicability domain. By linking neurodevelopmental disease‐related pathways to key neurodevelopmental processes, the work enhances
Eliska Kuchovska +14 more
wiley +1 more source
Limit theorems for bifurcating integer-valued autoregressive processes [PDF]
We study the asymptotic behavior of the weighted least squares estimators of the unknown parameters of bifurcating integer-valued autoregressive processes.
Blandin, Vassili
core +1 more source

