Nicolo Cesa-Bianchi, Philip M. Long, Manfred K. Warmuth  Home/Search
Context Related
| neurocolt.org/abs/...nctr96011.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: neurocolt.org/abs/1996...abs96011 (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: In this paper we study the performance of gradient descent when applied to the problem of on-line linear prediction in arbitrary inner product spaces. We show worst-case bounds on the sum of the squared prediction errors under various assumptions concerning the amount of a priori information about the sequence to predict. The algorithms we use are variants and extensions of on-line gradient descent. Whereas our algorithms always predict using linear functions as hypotheses, none of our results... (Update)
Context of citations to this paper: More
..., whose predictions are kept hidden from the master. Using this sequential prediction model, we will show (extending results from [3, 10, 12]) that a well known algorithm for linear regression, Gradient Descent, and a recently proposed variant, Exponentiated Gradient, have a...
Cited by: More
Analysis of Two Gradient-based Algorithms for On-line Regression - Dsi (1999) (Correct)
Similar documents (at the sentence level):
72.4%: Worst-case Quadratic Loss Bounds for On-line Prediction .. - Cesa-Bianchi, Long.. (1993) (Correct)
Active bibliography (related documents): More All
0.9: On the Complexity of Function Learning - Auer, Long, Maass, Woeginger (1994) (Correct)
0.5: Efficient Higher-order Neural Networks for Classification and.. - Ghosh, Shin (1995) (Correct)
0.3: New Adaptive-Filtering Techniques Applied To Speech Echo.. - Siqueira, Alwan (Correct)
Similar documents based on text: More All
0.4: On Bayes Methods for On-line Boolean Prediction - Cesa-Bianchi, Helmbold, Panizza (1997) (Correct)
0.4: The Perceptron algorithm vs. Winnow: linear vs. logarithmic.. - Kivinen, Warmuth (1997) (Correct)
0.4: Report for Publication of the Activity of the Working Group.. - Shawe-Taylor (1997) (Correct)
BibTeX entry: (Update)
N. Cesa-Bianchi, P.M. Long, and M.K. Warmuth. Worst-case quadratic loss bounds for prediction using linear functions and gradient descent. IEEE Transactions on Neural Networks, 7(3):604--619, 1996. http://citeseer.ist.psu.edu/cesa-bianchi96worstcase.html More
@article{ cesabianchi96worstcase,
author = "N. Cesa-Bianchi and P. M. Long and M. K. Warmuth",
title = "Worst-Case Quadratic Loss Bounds for Prediction Using Linear Functions and Gradient Descent",
journal = "IEEE Transactions on Neural Networks",
volume = "7",
number = "3",
month = "May",
pages = "604--619",
year = "1996",
url = "citeseer.ist.psu.edu/cesa-bianchi96worstcase.html" }
Citations (may not include all citations):2441 The Johns Hopkins University Press (context) - Golub, Van Loan - 1990
2133 Pattern Classification and Scene Analysis (context) - Duda, Hart - 1973
815 Adaptive Filter Theory (context) - Haykin - 1991
708 Cambridge University Press (context) - Horn, Johnson - 1985
530 Linear and Nonlinear Programming (context) - Luenberger - 1984
441 Queries and concept learning (context) - Angluin - 1988
373 Adaptive signal processing (context) - Widrow, Stearns - 1985
317 Learning quickly when irrelevant attributes abound: a new li.. (context) - Littlestone - 1988
222 Adaptive switching circuits (context) - Widrow, Hoff - 1960
214 Universal approximation bounds for superpositions of a sigmo.. (context) - Barron - 1993
133 Aggregating strategies (context) - Vovk - 1990
118 How to use expert advice (context) - Cesa-Bianchi, Freund et al. - 1993
88 Exponentiated gradient versus gradient descent for linear pr.. - Kivinen, Warmuth - 1994
81 Universal prediction of individual sequences (context) - Feder, Merhav et al. - 1992
74 Mistake Bounds and Logarithmic Linear-threshold Learning Alg.. (context) - Littlestone - 1989
35 Statistical theory: The prequential approach (context) - Dawid - 1984
32 line learning of linear functions - Littlestone, Long et al. - 1991
24 Angenaherte Auflosung von systemen linearer gleichungen (context) - Kaczmarz - 1937
12 Techniques of adaptive equalization of digital communication.. (context) - Lucky - 1966
12 Universal sequential learning and decision from individual d.. (context) - Merhav, Feder - 1992
9 Smoothing Techniques (context) - Hardle - 1991
8 A learning algorithm for linear operators (context) - Mycielski - 1988
5 The learning complexity of smooth functions of a single vari.. (context) - Kimber, Long - 1992
3 An adaptive echo canceller (context) - Sondhi - 1967
3 Silencing echoes in the telephone network (context) - Sondhi, Berkley - 1980
2 Applications of learning theorems (context) - Faber, Mycielski - 1991
2 General learning theorems (context) - Mycielski, Swierczkowski - 1991
2 A preliminary version appeared in the Proceedings of the 30t.. (context) - Littlestone, Warmuth et al. - 1991
2 Robust stability analysis of adaptation algorithms for singl.. (context) - Hui, Zak - 1991
1 A Proof of Theorem 4 (context) - Young, to et al. - 1988
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC