Exploration Using Without-Replacement Sampling of Actions Is Sometimes Inferior
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 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 کاملLattice Paths, Sampling without Replacement, and the Kernel Method
In this work we consider weighted lattice paths in the quarter plane N0 × N0. The steps are given by (m, n) → (m − 1, n), (m, n) → (m, n − 1) and are weighted as follows: (m, n)→ (m− 1, n) by m/(m + n) and step (m, n)→ (m, n− 1) by n/(m + n). The considered lattice paths are absorbed at lines y = x/t− s/t with t ∈ N and s ∈ N0. We provide explicit formulæ for the sum of the weights of paths, st...
متن کاملLattice Paths, Sampling Without Replacement, and Limiting Distributions
In this work we consider weighted lattice paths in the quarter plane N0 × N0. The steps are given by (m,n) → (m − 1, n), (m,n) → (m,n − 1) and are weighted as follows: (m,n) → (m − 1, n) by m/(m + n) and step (m,n) → (m,n − 1) by n/(m + n). The considered lattice paths are absorbed at lines y = x/t − s/t with t ∈ N and s ∈ N0. We provide explicit formulæ for the sum of the weights of paths, sta...
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: Machine Learning and Knowledge Extraction
سال: 2019
ISSN: 2504-4990
DOI: 10.3390/make1020041