کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6958080 | 1451936 | 2017 | 46 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Effective sample size for importance sampling based on discrepancy measures
ترجمه فارسی عنوان
اندازه نمونه موثر برای نمونه گیری اهمیت بر اساس اقدامات اختلاف
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
اندازه نمونه موثر، ناراحتی نمونه برداری اهمیت، مونت کارلو توزیع، فیلتر کردن ذرات، استنتاج بیزی،
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
پردازش سیگنال
چکیده انگلیسی
The Effective Sample Size (ESS) is an important measure of efficiency of Monte Carlo methods such as Markov Chain Monte Carlo (MCMC) and Importance Sampling (IS) techniques. In the IS context, an approximation ESS^ of the theoretical ESS definition is widely applied, involving the inverse of the sum of the squares of the normalized importance weights. This formula, ESS^, has become an essential piece within Sequential Monte Carlo (SMC) methods, to assess the convenience of a resampling step. From another perspective, the expression ESS^ is related to the Euclidean distance between the probability mass described by the normalized weights and the discrete uniform probability mass function (pmf). In this work, we derive other possible ESS functions based on different discrepancy measures between these two pmfs. Several examples are provided involving, for instance, the geometric mean of the weights, the discrete entropy (including the perplexity measure, already proposed in literature) and the Gini coefficient among others. We list five theoretical requirements which a generic ESS function should satisfy, allowing us to classify different ESS measures. We also compare the most promising ones by means of numerical simulations.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Signal Processing - Volume 131, February 2017, Pages 386-401
Journal: Signal Processing - Volume 131, February 2017, Pages 386-401
نویسندگان
Luca Martino, VÃctor Elvira, Francisco Louzada,