- Improved Approximation of Linear Threshold Functions Ilias Diakonikolas
- Quantum versus Classical Learnability Rocco A. Servedio Steven J. Gortler
- Maximum Margin Algorithms with Boolean Roni Khardon 1 and Rocco A. Servedio 2
- On Learning Monotone DNF under Product Distributions
- Learning Monotone Decision Trees in Polynomial Time Ryan O'Donnell #
- Extremal properties of polynomial threshold functions Ryan O'Donnell #
- Learning juntas Elchanan Mossel
- EQUIVALENCES AND SEPARATIONS BETWEEN QUANTUM AND CLASSICAL LEARNABILITY #
- DistributionFree Testing Lower Bounds for Basic Boolean Functions
- Improved Approximation of Linear Threshold Functions # Ilias Diakonikolas +
- Testing monotone highdimensional distributions Ronitt Rubinfeld
- Boosting and HardCore Sets Adam R. Klivans
- Learning Geometric Concepts via Gaussian Surface Area Adam R. Klivans
- Learning random logdepth decision trees under the uniform distribution
- Computing sparse permanents faster Rocco A. Servedio Andrew Wan
- Quantum versus Classical Learnability Rocco A. Servedio Steven J. Gortler
- On PAC Learning Using Winnow, Perceptron, and a PerceptronLike Algorithm Rocco A. Servedio \Lambda
- Efficiently Testing Sparse GF (2) Polynomials Ilias Diakonikolas, Homin K. Lee, Kevin Matulef,
- Separating Quantum and Classical Learning Rocco A. Servedio
- PAC Learning Mixtures of AxisAligned Gaussians with No Separation Assumption
- Attributeefficient learning of decision lists and linear threshold functions
- Learning random monotone DNF Je#rey C. Jackson #
- Polynomial Certi cates for Propositional Marta Arias 1 , Roni Khardon 1 , and Rocco A. Servedio 2
- Journal of Artificial Intelligence Research 24 (2005) 341356 Submitted 11/04; published 09/05 E#ciency versus Convergence of Boolean Kernels for
- On the Limits of Efficient Teachability Rocco A. Servedio \Lambda
- Learning Intersections and Thresholds of Halfspaces Adam R. Klivans #
- Hardness Results for Agnostically Learning Low-Degree Polynomial Threshold Functions
- PAC Analogues of Perceptron and Winnow via Boosting the Margin Rocco A. Servedio \Lambda
- Adaptive Martingale Boosting Philip M. Long
- Boosting the Area Under the ROC Curve Philip M. Long
- On PAC Learning Using Winnow, Perceptron, and a Perceptron-Like Algorithm Rocco A. Servedio
- Every linear threshold function has a lowweight approximator Rocco A. Servedio #
- Monotone Boolean Formulas can Approximate Monotone Linear Threshold Functions
- Machine Learning manuscript No. (will be inserted by the editor)
- Testing Fourier dimensionality and sparsity Parikshit Gopalan, Ryan O'Donnell, Rocco A. Servedio,
- Optimal Cryptographic Hardness of Learning Monotone Functions
- Learning DNF from Random Walks Nader Bshouty
- Testing 1-Weight Halfspaces Kevin Matulef1
- Learning Geometric Concepts via Gaussian Surface Area Adam R. Klivans
- One-Pass Boosting Zafer Barutcuoglu
- Learning Intersections and Thresholds of Halfspaces Adam R. Klivans
- Journal of Artificial Intelligence Research 24 (2005) 341-356 Submitted 11/04; published 09/05 Efficiency versus Convergence of Boolean Kernels for
- On Learning Monotone DNF under Product Distributions
- EQUIVALENCES AND SEPARATIONS BETWEEN QUANTUM AND CLASSICAL LEARNABILITY
- PAC Analogues of Perceptron and Winnow via Boosting the Margin Rocco A. Servedio
- Boosting and Hard-Core Sets Adam R. Klivans
- Separating Quantum and Classical Learning Rocco A. Servedio 1
- A bijective proof on circular compositions Rocco Servedio, YeongNan Yeh
- Boosting in the Presence of Noise Adam Tauman Kalai #
- OnePass Boosting Zafer Barutcuoglu
- Ecient Algorithms in Computational Learning Theory
- Unsupervised Evidence Integration Philip M. Long plong@cs.columbia.edu
- Learning DNF in Time 2 Adam R. Klivans #
- Optimal Cryptographic Hardness of Learning Monotone Functions
- Agnostically Learning Halfspaces Adam Tauman Kalai
- Learning DNF in Time 2 Adam R. Klivans
- On Learning Embedded Midbit Functions Rocco A. Servedio 1
- Learning Intersections of Halfspaces with a Adam R. Klivans ?1 and Rocco A. Servedio 2
- DNF are Teachable in the Average Case Homin K. Lee, Rocco A. Servedio # , and Andrew Wan ##
- arXiv:cs.CC/0508071 Every decision tree has an influential variable
- Testing for Concise Representations Ilias Diakonikolas #
- Martingale Boosting # Philip M. Long
- Discriminative Learning can Succeed where Generative Learning Fails #
- THE CHOW PARAMETERS PROBLEM RYAN O'DONNELL # AND ROCCO A. SERVEDIO +
- Toward Attribute E#cient Learning of Decision Lists and Parities
- Boosting the Area Under the ROC Curve Philip M. Long
- A Regularity Lemma, and Low-weight Approximators, for Low-degree Polynomial Threshold Functions
- Computational Sample Complexity and AttributeEfficient Rocco A. Servedio \Lambda
- New degree bounds for polynomial threshold functions # Ryan O'Donnell +
- Learning Unions of #(1)Dimensional Rectangles Alp Atc 1 and Rocco A. Servedio #
- Testing Halfspaces Kevin Matulef #
- Lower Bounds and Hardness Amplification for Learning Shallow Monotone Formulas
- A canonical form for testing Boolean function properties Dana Dachman-Soled
