Howard Aizenstein, Tibor Hegedüs, Lisa Hellerstein, Leonard Pitt  Home/Search
Context Related
| uiuc.edu/~pitt/Pape...queryhardness.ps 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: uiuc.edu/~pitt/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We investigate the complexity of learning for the well-studied model in which the learning algorithm may ask membership and equivalence queries. While complexity theoretic techniques have previously been used to prove hardness results in various learning models, these techniques typically are not strong enough to use when a learning algorithm may make membership queries. We develop a general technique for proving hardness results for learning with membership and equivalence queries (and... (Update)
Context of citations to this paper: More
.... (occurrences of each variable) in a formula, a restriction that has been well investigated in the learning theory literature [3, 38, 9, 10, 39, 1, 2]. Previous work has shown that it is possible to identify an arbitrary monotone read once ( formula under a stronger notion of...
...problems on 1 decision lists. We consider recognition from a formula (also called membership problem [20] and representation problem [4, 1]) and problems in the context of partially defined Boolean functions. A partially defined Boolean function (pdBf) can be viewed as a...
Cited by: More
On the Complexity of Training a Single Perceptron with.. - Síma (Correct)
The Complexity of Learning Concept Classes with Polynomial.. - Köbler, Lindner (2002) (Correct)
Conjunctions of Unate DNF Formulas: Learning and Structure - Feigelson, Hellerstein (1998) (Correct)
Active bibliography (related documents): More All
0.7: On the Geometric Separability of Boolean Functions - Hegedüs, Megiddo (1995) (Correct)
0.5: Learning Read-Once Formulas with Queries - Angluin, Hellerstein, Karpinski (1989) (Correct)
0.5: Graph Sandwich Problems - Golumbic, Kaplan, Shamir (1994) (Correct)
Similar documents based on text: More All
0.6: Learning k-term DNF Formulas with an Incomplete Membership.. - Goldman, Mathias (1992) (Correct)
0.5: Learning Boolean Read-Once Formulas over Generalized Bases - Bshouty, Hancock.. (1995) (Correct)
0.5: An Algorithm to Learn Read-Once Threshold Formulas, and some.. - Bshouty, al. (1993) (Correct)
Related documents from co-citation: More All
8: Queries and concept learning (context) - Angluin - 1988
7: the Limits of Proper Learnability of Subclasses of DNF Formulas (context) - Pillaipakkamnatt, Raghavan - 1994
5: Learning when irrelevant attributes abound: A new linear-threshold algorithm (context) - Littlestone - 1988
BibTeX entry: (Update)
H. Aizenstein, T. Hegedus, L. Hellerstein, and L. Pitt. Complexity Theoretic Hardness Results for Query Learning. Journal of Complexity, 1998. to appear. http://citeseer.ist.psu.edu/aizenstein98complexity.html More
@article{ aizenstein98complexity,
author = "Howard Aizenstein and Tibor Hegedus and Lisa Hellerstein and Leonard Pitt",
title = "Complexity Theoretic Hardness Results for Query Learning",
journal = "Computational Complexity",
volume = "7",
number = "1",
pages = "19-53",
year = "1998",
url = "citeseer.ist.psu.edu/aizenstein98complexity.html" }
Citations (may not include all citations):493 Communications of the ACM (context) - Valiant, of et al. - 1984
488 Algorithmic Graph Theory and Perfect Graphs (context) - Golumbic - 1980
441 Queries and concept learning (context) - Angluin - 1988
244 Learning regular sets from queries and counterexamples (context) - Angluin - 1987
184 Cryptographic limitations on learning Boolean formulae and f.. - Kearns, Valiant - 1994
149 Information Processing Letters (context) - Blumer, Ehrenfeucht et al. - 1987
144 Computational limitations on learning from examples (context) - Pitt, Valiant - 1988
129 Theoretical Computer Science (context) - Stockmeyer, hierarchy - 1976
105 Word problems requiring exponential time (context) - Stockmeyer, Meyer - 1973
101 Threshold logic and its applications (context) - Muroga - 1971
97 Learning read-once formulas with queries - Angluin, Hellerstein et al. - 1993
84 Learning conjunctions of Horn clauses - Angluin, Frazier et al. - 1992
82 When won't membership queries help (context) - Angluin, Kharitonov - 1991
78 the learnability of Boolean formulae - Kearns, Li et al. - 1987
74 Exact learning via the monotone theory (context) - Bshouty - 1993
66 Computational learning theory: survey and selected bibliogra.. (context) - Angluin - 1992
59 Prediction preserving reducibility (context) - Pitt, Warmuth - 1990
57 Oracles and queries that are sufficient for exact learning - Bshouty, Cleve et al. - 1994
54 Learning conjunctive concepts in structural domains (context) - Haussler - 1989
48 Classifying learnable geometric concepts with the Vapnik-Che.. (context) - Blumer, Ehrenfeucht et al. - 1986
46 An efficient membership-query algorithm for learning DNF wit.. - Jackson - 1994
45 The minimum consistent DFA problem cannot be approximated wi.. (context) - Pitt, Warmuth - 1993
36 How many queries are needed to learn - Hellerstein, Pillaipakkamnatt et al. - 1995
35 The complexity of the partial order dimension problem (context) - Yannakakis - 1982
27 term DNF formulas using queries and counterexamples (context) - Angluin, k- - 1987
26 Algorithms and lower bounds for on-line learning of geometri.. (context) - Maass, Tur'an - 1994
26 How fast can a threshold gate learn (context) - Maass, Turan - 1994
26 Learning arithmetic readonce formulas (context) - Bshouty, Hancock et al. - 1995
26 Training a 3-node neural net is NP-Complete (context) - Blum, Rivest - 1989
22 Read-thrice DNF is hard to learn with membership and equival.. (context) - Aizenstein, Hellerstein et al. - 1992
17 Learning functions of k terms (context) - Blum, Singh - 1990
17 Separating distribution-free and mistake-bound learning mode.. (context) - Blum - 1994
15 On learning ring-sum-expansions (context) - Fischer, Simon - 1992
13 An algorithm to learn read-once threshold formulas - Bshouty, Hancock et al. - 1994
13 the Learnability of Disjunctive Normal Form Formulas and Dec.. (context) - Aizenstein - 1993
12 Learning in neural networks (context) - Judd - 1988
12 the limits of proper learnability of subclasses of DNF formu.. (context) - Pillaipakkamnatt, Raghavan - 1994
10 A note on the production of matroid minors (context) - Seymour - 1977
10 Read-twice dnf formulas are properly learnable (context) - Pillaipakkamnatt, Raghavan - 1994
9 Combinatorial characterization of read-once formulae - Karchmer, Linial et al. - 1993
9 Polynomial time learnability of simple deterministic languag.. (context) - Ishizaka - 1990
8 Learning boolean readonce formulas over generalized bases - Bshouty, Hancock et al. - 1995
7 Theoretical Computer Science (context) - Board, Pitt et al. - 1992
7 Complexity results on learning by neural networks (context) - Lin, Vitter - 1991
7 Threshold Numbers and Threshold Completions (context) - Hammer, Ibaraki et al. - 1981
6 Learning switch configurations (context) - Raghavan, Schach - 1990
6 Generalized teaching dimensions and the query complexity of .. (context) - us - 1995
6 Exact learning of -DNF formulas with malicious membership qu.. (context) - Angluin - 1994
5 Aggregation of inequalities in integer programming (context) - Chvatal, Hammer - 1977
5 A graph theoretic characterization of the pv chunk class of .. (context) - Henderson, Zalcstein - 1977
4 On characterizing and learning some classes of read-once fun.. (context) - Hellerstein - 1989
3 On repetition-free boolean functions (context) - Gurvich - 1977
2 Departament de Llenguatges i sistemes inform`atics (context) - Gavald, The et al. - 1994
2 Three \Sigma 2 -Complete problems in computational learning .. (context) - Ko, Tzeng - 1991
2 Threshold decompositions of boolean functions and graphs (context) - Tyshkevich, Chernyak - 1989
1 Complete sets for the polynomial time hierarchy (context) - Wrathall - 1976
1 a learnability question associated to neural networks with c.. - DasGupta, Siegelmann et al. - 1994
1 On training simple neural networks and small-weight neurons (context) - us - 1994
1 Special Issue on Computational Learning Theory (context) - Angluin, for et al. - 1990
1 Can complexity theory benefit from learning theory (context) - us - 1993
1 Manuscript submitted for publication (context) - Aizenstein, Blum et al. - 1994
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www-sal.cs.uiuc.edu/~pitt/): More
On Exploiting Knowledge and Concept Use in Learning Theory - Pitt (Correct)
Learning Conjunctions of Horn Clauses - Angluin, Frazier, Pitt (1992) (Correct)
Criteria for Polynomial Time (Conceptual) Clustering - Pitt, Reinke (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