G. M. Benedek and A. Itai. Dominating distributions and learnability. In Proc. 5th Annu. Workshop on Comput. Learning Theory, pages 253--264. ACM Press, New York, NY, 1992. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Probabilistic Analysis of Learning in Artificial Neural Networks: .. - Anthony (1994) (10 citations) (Correct)
....distribution satisfies 1 Gamma (S k ) O(k Gammafi ) for some fi 0, then any consistent learning algorithm for H learns with respect to and has polynomial sample complexity. For further discussion of distribution dependent learning, we refer the reader to the papers of Benedek and Itai [32], Ben David, Benedek and Mansour [27] Bertoni et al. 33] Kharitonov [66] Li and Vitanyi [68] Linial, Mansour and Nisan [69] Graph Dimension and Multiple Output Nets 42 11 Graph Dimension and Multiple Output Nets The basic PAC model concerns learning f0; 1g valued functions only; that is, ....
G. M. Benedek and A. Itai. Dominating distributions and learnability. In Proc. 5th Annu. Workshop on Comput. Learning Theory, pages 253--264. ACM Press, New York, NY, 1992.
Computational Learning Theory for Artificial Neural Networks - Anthony, Biggs (1993) (2 citations) (Correct)
....is necessary when P consists of all distributions. In addition, learning with respect to a particular distribution may be computationally feasible in situations where standard pac learning is NP hard. For further discussion of distribution dependent learning, we refer the reader to the papers of Benedek and Itai (1992), Ben David, Benedek and Mansour (1989) Bertoni et al. 1992) Kharitonov (1993) Li and Vitanyi (1989) Linial, Mansour and Nisan (1989) In the standard pac framework, the learning algorithm receives labelled examples and forms a hypothesis only on the basis of these. The learning algorithm ....
Benedek and Itai (1992): G. Benedek and A. Itai, Dominating distributions and learnability, In Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, ACM Press, New York.
Efficient Learning from Faulty Data - Decatur (1995) (1 citation) (Correct)
....under distributions in D. Therefore, when given an arbitrary distribution D of distance fl to some distribution in D, we cannot hope in general to achieve an error rate much better than fl=2. 2 Yet, we can achieve error rates better than fl=2 if we consider dominating distributions as defined by Benedek and Itai (1992). They use dominating distributions to specify when learnability with one distribution implies learnability 2 For example, consider instance space f0; 1g Thetaf0; 1g n and a function class in which each function is defined to be a conjunction of the final n bits if the first bit is 0 or an ....
Benedek, Gyora and Alon Itai. (1992). Dominating distributions and learnability.
Statistical Queries and Faulty PAC Oracles - Decatur (1993) (30 citations) (Correct)
....or very small weight under distributions in D. Therefore, when given an arbitrary distribution D of distance fl to some distribution in D, we cannot hope in general to get better than error fl. We can avoid this situation if we consider dominating distributions as defined by Benedek and Itai [6]. They use dominating distributions to specify when learning with one distribution implies learning with another. They say D 1 dominates D 2 if for every x 2 X, D 1 (x) 0 implies D 2 (x) 0. In addition, for ff 1, D 1 ff dominates D 2 if for every x 2 X, D 2 (x) ffD 1 (x) Definition 11 We ....
G. Benedek and A. Itai. Dominating distributions and learnability. In Proceedings of COLT '92, pages 253-- 264. Morgan Kaufmann, 1992.
Probabilistic Learning Theory, with Emphasis on Sample Complexity - Anthony (Correct)
....is non decreasing, VCdim(HjS k ) k and 1 Gamma (S k ) O(k Gammafi ) for some fi 0, then any consistent learning algorithm for H learns with respect to and has polynomial sample complexity. For further discussion of distribution dependent learning, we refer the reader to the papers of Benedek and Itai (1992), Ben David, Benedek and Mansour (1989) Bertoni et al. 1992) Kharitonov (1993) Li and Vitanyi (1989) Linial, Mansour and Nisan (1989) 7. GENERALISING THE VC DIMENSION FOR FUNCTION SPACES The basic pac model concerns learning f0; 1g valued functions only; that is, it is concerned only with ....
Benedek and Itai (1992): G. Benedek and A. Itai, Dominating distributions and learnability, In Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, ACM Press, New York.
Probabilistic Analysis of Learning in Artificial Neural Networks: .. - Anthony (1997) (10 citations) (Correct)
....distribution satisfies 1 Gamma (S k ) O(k Gammafi ) for some fi 0, then any consistent learning algorithm for H learns with respect to and has polynomial sample complexity. For further discussion of distribution dependent learning, we refer the reader to the papers of Benedek and Itai [34], Ben David, Benedek and Mansour [29] Bertoni et al. 35] Kharitonov [74] Li and Vitanyi [77] Linial, Mansour and Nisan [78] For discussion specific to neural networks, see [52, 86] 11 Graph Dimension and Multiple Output Nets The basic PAC model concerns learning f0; 1g valued functions ....
G. M. Benedek and A. Itai. Dominating distributions and learnability. In Proc. 5th Annu. Workshop on Comput. Learning Theory, pages 253--264. ACM Press, New York, NY, 1992.
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