一个普森采样算法与对数后悔为单模式高斯强盗
IEEE transactions on neural networks and learning systems
|August 1, 2023
概括
这项研究介绍了一种新的普森采样算法,用于单模式盗问题. 该算法有效地探索武器,实现最佳的O ((logT) 遗憾,与最先进的方法相比.
科学领域:
- 机器学习 机器学习
- 优化算法 优化算法
- 统计推理 统计推理
背景情况:
- 多重武装强盗 (MAB) 问题涉及在不确定性下进行连续的决策.
- 单模MAB (U-MAB) 设置在预期奖励中假设了一个特定的结构,允许更高效的探索.
- 现有的算法可能无法充分利用单模结构以获得最佳性能.
研究的目的:
- 提出一个针对高斯奖励的单模式强盗问题量身定制的普森抽样算法.
- 通过将探索重点放在有前途的武器社区上来加强决策.
- 从理论和经验上验证算法的性能和遗憾的界限.
主要方法:
- 开发一个普森采样算法,利用高斯先验.
- 实施以后分布和经验手段为指导的基于社区的勘探策略.
- 理论分析来得出非对称的遗憾边界.
- 在合成和现实世界数据集上的实证评估.
主要成果:
- 拟议的算法实现了O ((logT) 的非对称遗憾.
- 这种遗憾的边界是异常最优的,可以与现有的最先进的U-MAB算法进行比较.
- 实验结果证明了算法的有效性和效率.
结论:
- 新的普森抽样算法有效地利用了单模式奖励结构.
- 基于社区的勘探策略显著提高了决策效率.
- 该算法为单模式多武器强盗问题提供了具有竞争力和有效的解决方案.
相关概念视频
Sampling Distribution
13.0K
Given simple random samples of size n from a given population with a measured characteristic such as mean, proportion, or standard deviation for each sample, the probability distribution of all the measured characteristics is called a sampling distribution. How much the statistic varies from one sample to another is known as the sampling variability of a statistic. You typically measure the sampling variability of a statistic by its standard error. The standard error of the mean is an example...
13.0K
Sampling Theorem
384
In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.
384
Bandpass Sampling
206
In signal processing, bandpass sampling is an effective technique for sampling signals that have most of their energy concentrated within a narrow frequency band. This type of signal is known as a bandpass signal. The key principle of bandpass sampling involves sampling the signal at a rate that is greater than twice the signal's bandwidth to prevent aliasing.
A bandpass signal has a spectrum with a lower frequency limit, denoted as ω1, and an upper frequency limit, denoted as ω2....
A bandpass signal has a spectrum with a lower frequency limit, denoted as ω1, and an upper frequency limit, denoted as ω2....
206
Sampling Continuous Time Signal
278
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
278
Propagation of Uncertainty from Random Error
726
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
726
Estimating Population Mean with Known Standard Deviation
8.7K
To construct a confidence interval for a single unknown population mean μ, where the population standard deviation is known, we need sample mean as an estimate for μ and we need the margin of error. Here, the margin of error (EBM) is called the error bound for a population mean (abbreviated EBM). The sample mean is the point estimate of the unknown population mean μ.
The confidence interval estimate will have the form as follows:
(point estimate - error bound, point estimate +...
The confidence interval estimate will have the form as follows:
(point estimate - error bound, point estimate +...
8.7K


