Randomization without replacement using replacement without losing your place
نویسندگان
چکیده
منابع مشابه
Without-Replacement Sampling for Stochastic Gradient Methods
Stochastic gradient methods for machine learning and optimization problems are usually analyzed assuming data points are sampled with replacement. In contrast, sampling without replacement is far less understood, yet in practice it is very common, often easier to implement, and usually performs better. In this paper, we provide competitive convergence guarantees for without-replacement sampling...
متن کاملWeighted Sampling Without Replacement from Data Streams
Weighted sampling without replacement has proved to be a very important tool in designing new algorithms. Efraimidis and Spirakis (IPL 2006) presented an algorithm for weighted sampling without replacement from data streams. Their algorithm works under the assumption of precise computations over the interval [0, 1]. Cohen and Kaplan (VLDB 2008) used similar methods for their bottom-k sketches. ...
متن کاملTest case selection with and without replacement
Previous theoretical studies on the eectiveness of partition testing and random testing have assumed that test cases are selected with replacement. Although this assumption has been well known to be less realistic, it has still been used in previous theoretical work because it renders the analyses more tractable. This paper presents a theoretical investigation aimed at comparing the eectivene...
متن کاملEditorial: Aortic Valve Replacement Without Myocardial Revascularization
BONOW AND COLLEAGUES,' in the preceding paper, concluded that coronary artery bypass grafting (CABG) at the time of aortic valve replacement (AVR) is not advantageous as a near-routine procedure for patients with combined important aortic valve and coronary artery disease. We believe that such a conclusion is premature and unwarranted. The information that is required for making a reliable stat...
متن کاملAccelerating weighted random sampling without replacement
Random sampling from discrete populations is one of the basic primitives in statistical computing. This article briefly introduces weighted and unweighted sampling with and without replacement. The case of weighted sampling without replacement appears to be most difficult to implement efficiently, which might be one reason why the R implementation performs slowly for large problem sizes. This p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Behavior Research Methods & Instrumentation
سال: 1978
ISSN: 1554-351X,1554-3528
DOI: 10.3758/bf03205167