On efficient agnostic learning of linear combinations of basis functions
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
The importance of convexity in learning with squared loss
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Journal of the ACM (JACM)
Algorithmic stability and sanity-check bounds for leave-one-out cross-validation
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Agnostic learning of geometric patterns (extended abstract)
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
The complexity of learning according to two models of a drifting environment
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
On the sample complexity of learning functions with bounded variation
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Sample-efficient strategies for learning in the presence of noise
Journal of the ACM (JACM)
The Complexity of Learning According to Two Models of a Drifting Environment
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Theoretical Computer Science
Learning to recognize three-dimensional objects
Neural Computation
ECML '02 Proceedings of the 13th European Conference on Machine Learning
Optimized Substructure Discovery for Semi-structured Data
PKDD '02 Proceedings of the 6th European Conference on Principles of Data Mining and Knowledge Discovery
On the Generalization Ability of Recurrent Networks
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Discovering Unordered and Ordered Phrase Association Patterns for Text Mining
PADKK '00 Proceedings of the 4th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Current Issues and New Applications
A Fast Algorithm for Discovering Optimal String Patterns in Large Text Databases
ALT '98 Proceedings of the 9th International Conference on Algorithmic Learning Theory
ALT '99 Proceedings of the 10th International Conference on Algorithmic Learning Theory
Learning Intermediate Concepts
ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
Optimally-Smooth Adaptive Boosting and Application to Agnostic Learning
ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
Efficient Data Mining from Large Text Databases
Progress in Discovery Science, Final Report of the Japanese Discovery Science Project
Efficient Discovery of Proximity Patterns with Suffix Arrays
CPM '01 Proceedings of the 12th Annual Symposium on Combinatorial Pattern Matching
Efficient Text Mining with Optimized Pattern Discovery
CPM '02 Proceedings of the 13th Annual Symposium on Combinatorial Pattern Matching
An Efficient Tool for Discovering Simple Combinatorial Patterns from Large Text Databases
DS '98 Proceedings of the First International Conference on Discovery Science
Characteristic Sets of Strings Common to Semi-structured Documents
DS '99 Proceedings of the Second International Conference on Discovery Science
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
On Agnostic Learning with {0, *, 1}-Valued and Real-Valued Hypotheses
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Maximizing Agreement with a Classification by Bounded or Unbounded Number of Associated Words
ISAAC '98 Proceedings of the 9th International Symposium on Algorithms and Computation
Multiple-Instance Learning of Real-Valued Geometric Patterns
Annals of Mathematics and Artificial Intelligence
On the difficulty of approximately maximizing agreements
Journal of Computer and System Sciences
Optimally-smooth adaptive boosting and application to agnostic learning
The Journal of Machine Learning Research
Cost-Sensitive Learning by Cost-Proportionate Example Weighting
ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
Efficient algorithms for learning functions with bounded variation
Information and Computation
Machine Learning
Some Dichotomy Theorems for Neural Learning Problems
The Journal of Machine Learning Research
Some connections between learning and optimization
Discrete Applied Mathematics - Discrete mathematics & data mining (DM & DM)
Agnostically Learning Halfspaces
FOCS '05 Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science
SODA '06 Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm
Clustering with qualitative information
Journal of Computer and System Sciences - Special issue: Learning theory 2003
Learning in natural language: theory and algorithmic approaches
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Tolerant property testing and distance approximation
Journal of Computer and System Sciences
Self-improved gaps almost everywhere for the agnostic approximation of monomials
Theoretical Computer Science
Noise Tolerant Variants of the Perceptron Algorithm
The Journal of Machine Learning Research
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
Agnostically learning decision trees
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
On agnostic boosting and parity learning
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
A note on the inapproximability of correlation clustering
Information Processing Letters
Property Testing: A Learning Theory Perspective
Foundations and Trends® in Machine Learning
Learning Halfspaces with Malicious Noise
ICALP '09 Proceedings of the 36th International Colloquium on Automata, Languages and Programming: Part I
Learning with annotation noise
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Some connections between learning and optimization
Discrete Applied Mathematics
Learning Halfspaces with Malicious Noise
The Journal of Machine Learning Research
Property testing: a learning theory perspective
COLT'07 Proceedings of the 20th annual conference on Learning theory
A lower bound for agnostically learning disjunctions
COLT'07 Proceedings of the 20th annual conference on Learning theory
ALT'09 Proceedings of the 20th international conference on Algorithmic learning theory
Algorithms and theory of computation handbook
Competing against the best nearest neighbor filter in regression
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
SIAM Journal on Computing
SIAM Journal on Computing
Learning hurdles for sleeping experts
Proceedings of the 3rd Innovations in Theoretical Computer Science Conference
Submodular functions are noise stable
Proceedings of the twenty-third annual ACM-SIAM symposium on Discrete Algorithms
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Approximation algorithms for minimizing empirical error by axis-parallel hyperplanes
ECML'05 Proceedings of the 16th European conference on Machine Learning
Hardness results for agnostically learning low-degree polynomial threshold functions
Proceedings of the twenty-second annual ACM-SIAM symposium on Discrete Algorithms
Learnability of bipartite ranking functions
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Nearly optimal solutions for the chow parameters problem and low-weight approximation of halfspaces
STOC '12 Proceedings of the forty-fourth annual ACM symposium on Theory of computing
On learning finite-state quantum sources
Quantum Information & Computation
Journal of Computer and System Sciences
A complete characterization of statistical query learning with applications to evolvability
Journal of Computer and System Sciences
An Improved Branch-and-Bound Method for Maximum Monomial Agreement
INFORMS Journal on Computing
Learning Kernel-Based Halfspaces with the 0-1 Loss
SIAM Journal on Computing
SIAM Journal on Computing
Activized learning: transforming passive to active with improved label complexity
The Journal of Machine Learning Research
An invariance principle for polytopes
Journal of the ACM (JACM)
PAC-Learning with general class noise models
KI'12 Proceedings of the 35th Annual German conference on Advances in Artificial Intelligence
Learnability beyond uniform convergence
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
Exploiting label dependencies for improved sample complexity
Machine Learning
Implicit learning of common sense for reasoning
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
| Hi-index | 0.00 |
In this paper we initiate an investigation of generalizations of the Probably Approximately Correct (PAC) learning model that attempt to significantly weaken the target function assumptions. The ultimate goal in this direction is informally termed agnostic learning, in which we make virtually no assumptions on the target function. The name derives from the fact that as designers of learning algorithms, we give up the belief that Nature (as represented by the target function) has a simple or succinct explanation. We give a number of positive and negative results that provide an initial outline of the possibilities for agnostic learning. Our results include hardness results for the most obvious generalization of the PAC model to an agnostic setting, an efficient and general agnostic learning method based on dynamic programming, relationships between loss functions for agnostic learning, and an algorithm for a learning problem that involves hidden variables.