Error bounds from extra-precise iterative refinement
نویسندگان
چکیده
منابع مشابه
Generalization Error Bounds for Noisy, Iterative Algorithms
In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bound on the generalization error of empirical risk minimization based on the mutual information I(S;W ) between the algorithm input S and the algorithm output W , when the loss f...
متن کاملGPU-Accelerated Asynchronous Error Correction for Mixed Precision Iterative Refinement
In hardware-aware high performance computing, blockasynchronous iteration and mixed precision iterative refinement are two techniques that are applied to leverage the computing power of SIMD accelerators like GPUs. Although they use a very different approach for this purpose, they share the basic idea of compensating the convergence behaviour of an inferior numerical algorithm by a more efficie...
متن کاملIterative refinement of range images with anisotropic error distribution
We propose a method which refines the range measurement of range finders by computing correspondences of vertices of multiple range images acquired from various viewpoints. Our method assumes that a range image acquired by a laser range finder has anisotropic error distribution which is parallel to the ray direction. Thus, we find corresponding points of range images along with the ray directio...
متن کاملError Rate Bounds and Iterative Weighted Majority Voting for Crowdsourcing
Crowdsourcing has become an effective and popular tool for human-powered computation to label large datasets. Since the workers can be unreliable, it is common in crowdsourcing to assign multiple workers to one task, and to aggregate the labels in order to obtain results of high quality. In this paper, we provide finite-sample exponential bounds on the error rate (in probability and in expectat...
متن کاملMajorizing Sequences and Error Bounds for Iterative Methods
Given a sequence {xn}n=Q in a Banach space, it is well known that if there a sequence {r^J^—QSUch that Wxn+X — xn\\ < tn + x — tn and lim tn = t* < °°, then {xn}n=Q converges to some x* and the error bounds IIjc* — jc II < f* — tn hold. It is shown that certain stronger hypotheses imply sharper error bounds, ■**-*„« <—-—Jxn-Xn-X*11* * \'*1-'0|M" > »• Representative applications to infinite seri...
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: ACM Transactions on Mathematical Software
سال: 2006
ISSN: 0098-3500,1557-7295
DOI: 10.1145/1141885.1141894