Online Gradient Descent Learning Algorithms
نویسندگان
چکیده
منابع مشابه
Online Gradient Descent Learning Algorithms
This paper considers the least-square online gradient descent algorithm in a reproducing kernel Hilbert space (RKHS) without explicit regularization. We present a novel capacity independent approach to derive error bounds and convergence results for this algorithm. We show that, although the algorithm does not involve an explicit RKHS regularization term, choosing the step sizes appropriately c...
متن کاملLearning by Online Gradient Descent
We study online gradient{descent learning in multilayer networks analytically and numerically. The training is based on randomly drawn inputs and their corresponding outputs as deened by a target rule. In the thermo-dynamic limit we derive deterministic diierential equations for the order parameters of the problem which allow an exact calculation of the evolution of the generalization error. Fi...
متن کاملOnline gradient descent learning algorithm†
This paper considers the least-square online gradient descent algorithm in a reproducing kernel Hilbert space (RKHS) without an explicit regularization term. We present a novel capacity independent approach to derive error bounds and convergence results for this algorithm. The essential element in our analysis is the interplay between the generalization error and a weighted cumulative error whi...
متن کاملOnline Learning, Stability, and Stochastic Gradient Descent
In batch learning, stability together with existence and uniqueness of the solution corresponds to well-posedness of Empirical Risk Minimization (ERM) methods; recently, it was proved that CVloo stability is necessary and sufficient for generalization and consistency of ERM ([9]). In this note, we introduce CVon stability, which plays a similar role in online learning. We show that stochastic g...
متن کاملDual Space Gradient Descent for Online Learning
One crucial goal in kernel online learning is to bound the model size. Common approaches employ budget maintenance procedures to restrict the model sizes using removal, projection, or merging strategies. Although projection and merging, in the literature, are known to be the most effective strategies, they demand extensive computation whilst removal strategy fails to retain information of the r...
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: Foundations of Computational Mathematics
سال: 2007
ISSN: 1615-3375,1615-3383
DOI: 10.1007/s10208-006-0237-y