Sally Floyd, Manfred Warmuth  Home/Search
Context Related
| ucsc.edu/pub/tr/ucsccrl9313.ps.Z 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: indiana.edu/pub/ucstri/index (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Within the framework of pac-learning, we explore the learnability of concepts from samples using the paradigm of sample compression schemes. A sample compression scheme of size d for a concept class C ` 2 X consists of a compression function and a reconstruction function. The compression function, given a finite sample set consistent with some concept in C, chooses a subset of k examples as the compression set. The reconstruction function, given a compression set of k examples,... (Update)
Context of citations to this paper: More
...at most k = O(1) examples and O(log log n) additional bits. The notion of space bounded learning appears, for example, in [AFHM93, Ame94, Ame95, Flo89, FW95]. In addition the set of hypotheses used by A must have a VC dimension of O(1) this implies in particular that VC...
...scheme for a class. We shall discuss several types of compression schemes, in the spirit of the schemes discussed by Floyd and Warmuth [FW95], each of these schemes gives rise to its own parameter) ffl The optimal mistake bound for learning the class online (sometimes called...
Cited by: More
PAC-MDL bounds - Avrim Blum And (2003) (Correct)
Combinatorial Variability of Vapnik-Chervonenkis Classes.. - Ben-David, Litman (Correct)
A Composition Theorem for Learning Algorithms with.. - Ben-David, Bshouty.. (1997) (Correct)
Similar documents (at the sentence level):
24.5%: Sample compression, learnability, and the Vapnik-Chervonenkis .. - Floyd, Warmuth (1995) (Correct)
Active bibliography (related documents): More All
0.3: Relating Data Compression and Learnability - Littlestone, Warmuth (1986) (Correct)
0.3: Teaching a Smarter Learner - Goldman, Mathias (1994) (Correct)
0.3: The Power of Self-Directed Learning - Goldman, Sloan (1991) (Correct)
Similar documents based on text: More All
0.2: Relative Loss Bounds for Entropy Based Updates (Preliminary.. - Herbater (Correct)
0.2: Theory, 1998. [BB, p.90] A. Blum and C. Burch. On-line.. - Proc Th Annu (Correct)
0.2: Tracking the Best Linear Predictor - Herbster (2001) (Correct)
Related documents from co-citation: More All
4: the uniform convergence of relative frequencies of events to their probabilities (context) - Vapnik, Chervonenkis - 1971
3: Quantitatively Tight Sample Complexity Bounds - Langford - 2002
3: Information Processing Letters (context) - Blumer, Ehrenfeucht et al. - 1987
BibTeX entry: (Update)
Sally Floyd and Manfred Warmuth, "Sample Compression, learnability, and the Vapnik-Chervonenkis Dimension," Machine Learning, 21, 269--304 (1995). http://citeseer.ist.psu.edu/floyd93sample.html More
@techreport{ floyd93sample,
author = "Sally Floyd and Manfred Warmuth",
title = "{SAMPLE} {COMPRESSION}, {LEARNABILITY}, {AND} {THE} {VAPNIK}-{CHERVONENKIS} {DIMENSION}",
number = "UCSC-CRL-93-13",
year = "1993",
url = "citeseer.ist.psu.edu/floyd93sample.html" }
Citations (may not include all citations):537 A theory of the learnable (context) - Valiant - 1984
465 Learnability and the VapnikChervonenkis Dimension (context) - Blumer, Ehrenfeucht et al. - 1989
454 the Uniform Convergence of Relative Frequencies of Events to.. (context) - Vapnik, Chervonenkis - 1971
273 The strength of weak learnability - Schapire - 1990
180 Boosting a weak learning algorithm by majority - Freund - 1990
151 A General Lower Bound on the Number of Examples Needed for L.. (context) - Ehrenfeucht, Haussler et al. - 1988
117 Estimation of Dependencies based on Empirical Data (context) - Vapnik - 1982
115 the Density of Families of Sets (context) - Sauer
96 Occam's Razor (context) - Blumer, Ehrenfeucht et al. - 1987
29 Learning Nested Differences of Intersection Closed Concept C.. (context) - Haussler, Sloan et al. - 1989
24 Bounding Sample Size with the VapnikChervonenkis Dimension (context) - Shawe-Taylor, Anthony et al. - 1989
21 Relating Data Compression and Learnability - Littlestone, Warmuth - 1986
12 On Space-bounded Learning and the Vapnik-Chervonenkis Dimens.. (context) - Floyd - 1989
5 Complete Range Spaces (context) - Welzl
3 Learning Faster than Promised by the VapnikChervonenkis Dime.. (context) - Blumer, Littlestone - 1989
1 Lower Bounds on PAC learning and the Size of Epsilon-Nets (context) - Haussler, Littlestone et al.
1 Hypothesis Schemas (context) - Littlestone, Schapire
1 Soem New Bounds for Epsilon-Nets (context) - Pach, Woeginger - 1990
1 A Appendix Proof of Theorem 6 (context) - Welzl, Woeginger - 1987
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cs.indiana.edu/pub/ucstri/index): More
Environment Modelling for Mobile Robots: Neural Learning for.. - van Dam (1998) (Correct)
Broadcasting in Butterfly and DeBruijn Networks - Klasing, Monien, Peine, Stöhr (1992) (Correct)
ILFA - A Project in Experimental Logic Computation - Dunker, Flögel, Büning.. (Correct)
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