Philip M. Long

168 papers A* 43A 3B 10Journal 94Unranked 18

Year	Rank	Type	Title / Venue / Authors
2024	J	`jnl`	Corrigendum to "Prediction, learning, uniform convergence, and scale-sensitive dimensions" [J. Comput. Syst. Sci. 56 (2) (1998) 174-190]. J. Comput. Syst. Sci. Peter L. Bartlett, Philip M. Long
2024	J	`jnl`	Sharpness-Aware Minimization and the Edge of Stability. J. Mach. Learn. Res. Philip M. Long, Peter L. Bartlett
2023	J	`jnl`	Deep linear networks can benignly overfit when shallow ones do. J. Mach. Learn. Res. Niladri S. Chatterji, Philip M. Long
2023	J	`jnl`	Prediction, Learning, Uniform Convergence, and Scale-sensitive Dimensions. CoRR Peter L. Bartlett, Philip M. Long
2023	J	`jnl`	Sharpness-Aware Minimization and the Edge of Stability. CoRR Philip M. Long, Peter L. Bartlett
2023	J	`jnl`	The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima. J. Mach. Learn. Res. Peter L. Bartlett, Philip M. Long, Olivier Bousquet
2022	J	`jnl`	Deep Linear Networks can Benignly Overfit when Shallow Ones Do. CoRR Niladri S. Chatterji, Philip M. Long
2022	J	`jnl`	Foolish Crowds Support Benign Overfitting. J. Mach. Learn. Res. Niladri S. Chatterji, Philip M. Long
2022	J	`jnl`	The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima. CoRR Peter L. Bartlett, Philip M. Long, Olivier Bousquet
2022	J	`jnl`	The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks. J. Mach. Learn. Res. Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2022	J	`jnl`	The Perils of Being Unhinged: On the Accuracy of Classifiers Minimizing a Noise-Robust Convex Loss. Neural Comput. Philip M. Long, Rocco A. Servedio
2021	J	`jnl`	Failures of Model-dependent Generalization Bounds for Least-norm Interpolation. J. Mach. Learn. Res. Peter L. Bartlett, Philip M. Long
2021	J	`jnl`	Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime. J. Mach. Learn. Res. Niladri S. Chatterji, Philip M. Long
2021	J	`jnl`	Foolish Crowds Support Benign Overfitting. CoRR Niladri S. Chatterji, Philip M. Long
2021	J	`jnl`	Properties of the After Kernel. CoRR Philip M. Long
2021	J	`jnl`	Superlinear Integrality Gaps for the Minimum Majority Problem. SIAM J. Discret. Math. Philip M. Long
2021	J	`jnl`	The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks. CoRR Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2021	J	`jnl`	The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss. CoRR Philip M. Long, Rocco A. Servedio
2021	J	`jnl`	When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? J. Mach. Learn. Res. Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2021	A*	`conf`	When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2021	J	`jnl`	When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? CoRR Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2020	J	`jnl`	Failures of model-dependent generalization bounds for least-norm interpolation. CoRR Peter L. Bartlett, Philip M. Long
2020	J	`jnl`	Finite-sample analysis of interpolating linear classifiers in the overparameterized regime. CoRR Niladri S. Chatterji, Philip M. Long
2020	A*	`conf`	Generalization bounds for deep convolutional neural networks. ICLR Philip M. Long, Hanie Sedghi
2020	J	`jnl`	New bounds on the price of bandit feedback for mistake-bounded online multiclass learning. Theor. Comput. Sci. Philip M. Long
2020	B	`conf`	On the Complexity of Proper Distribution-Free Learning of Linear Classifiers. ALT Philip M. Long, Raphael J. Long
2020	A*	`conf`	On the Global Convergence of Training Deep Linear ResNets. ICLR Difan Zou, Philip M. Long, Quanquan Gu
2020	J	`jnl`	On the Global Convergence of Training Deep Linear ResNets. CoRR Difan Zou, Philip M. Long, Quanquan Gu
2020	J	`jnl`	Oracle lower bounds for stochastic gradient sampling algorithms. CoRR Niladri S. Chatterji, Peter L. Bartlett, Philip M. Long
2020	J	`jnl`	When does gradient descent with logistic loss find interpolating two-layer networks? CoRR Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2019	J	`jnl`	Benign Overfitting in Linear Regression. CoRR Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler
2019	A	`conf`	Density Estimation for Shift-Invariant Multidimensional Distributions. ITCS Anindya De, Philip M. Long, Rocco A. Servedio
2019	J	`jnl`	Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks. Neural Comput. Peter L. Bartlett, David P. Helmbold, Philip M. Long
2019	J	`jnl`	On the Effect of the Activation Function on the Distribution of Hidden Nodes in a Deep Network. Neural Comput. Philip M. Long, Hanie Sedghi
2019	J	`jnl`	On the effect of the activation function on the distribution of hidden nodes in a deep network. CoRR Philip M. Long, Hanie Sedghi
2019	J	`jnl`	Size-free generalization bounds for convolutional neural networks. CoRR Philip M. Long, Hanie Sedghi
2019	—	`conf`	The Singular Values of Convolutional Layers. ICLR (Poster) Hanie Sedghi, Vineet Gupta, Philip M. Long
2018	J	`jnl`	Density estimation for shift-invariant multidimensional distributions. CoRR Anindya De, Philip M. Long, Rocco A. Servedio
2018	J	`jnl`	Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. CoRR Peter L. Bartlett, David P. Helmbold, Philip M. Long
2018	A*	`conf`	Gradient descent with identity initialization efficiently learns positive definite linear transformations. ICML Peter L. Bartlett, David P. Helmbold, Philip M. Long
2018	A*	`conf`	Learning Sums of Independent Random Variables with Sparse Collective Support. FOCS Anindya De, Philip M. Long, Rocco A. Servedio
2018	J	`jnl`	Learning Sums of Independent Random Variables with Sparse Collective Support. CoRR Anindya De, Philip M. Long, Rocco A. Servedio
2018	J	`jnl`	Representing smooth functions as compositions of near-identity functions with implications for deep network optimization. CoRR Peter L. Bartlett, Steven N. Evans, Philip M. Long
2018	J	`jnl`	The Singular Values of Convolutional Layers. CoRR Hanie Sedghi, Vineet Gupta, Philip M. Long
2017	—	`conf`	How to select a winner in evolutionary optimization? SSCI Risto Miikkulainen, Hormoz Shahrzad, Nigel Duffy, Philip M. Long
2017	B	`conf`	New bounds on the price of bandit feedback for mistake-bounded online multiclass learning. ALT Philip M. Long
2017	A*	`conf`	Surprising properties of dropout in deep networks. COLT David P. Helmbold, Philip M. Long
2017	J	`jnl`	Surprising properties of dropout in deep networks. J. Mach. Learn. Res. David P. Helmbold, Philip M. Long
2017	J	`jnl`	The Power of Localization for Efficiently Learning Linear Separators with Noise. J. ACM Pranjal Awasthi, Maria-Florina Balcan, Philip M. Long
2016	J	`jnl`	Dropout Versus Weight Decay for Deep Networks. CoRR David P. Helmbold, Philip M. Long
2015	J	`jnl`	On the inductive bias of dropout. J. Mach. Learn. Res. David P. Helmbold, Philip M. Long
2015	J	`jnl`	Special Issue on New Theoretical Challenges in Machine Learning. Algorithmica Avrim Blum, Philip M. Long
2014	A	`conf`	Benchmarking large-scale Fine-Grained Categorization. WACV Anelia Angelova, Philip M. Long
2014	J	`jnl`	On the Inductive Bias of Dropout. CoRR David P. Helmbold, Philip M. Long
2014	J	`jnl`	On the Weight of Halfspaces over Hamming Balls. SIAM J. Discret. Math. Philip M. Long, Rocco A. Servedio
2014	A*	`conf`	The power of localization for efficiently learning linear separators with noise. STOC Pranjal Awasthi, Maria-Florina Balcan, Philip M. Long
2013	A*	`conf`	Active and passive learning of linear separators under log-concave distributions. COLT Maria-Florina Balcan, Philip M. Long
2013	J	`jnl`	Algorithms and hardness results for parallel large margin learning. J. Mach. Learn. Res. Philip M. Long, Rocco A. Servedio
2013	—	`conf`	Consistency versus Realizable H-Consistency for Multiclass Classification. ICML (3) Philip M. Long, Rocco A. Servedio
2013	A	`conf`	Low-weight halfspaces for sparse boolean vectors. ITCS Philip M. Long, Rocco A. Servedio
2013	J	`jnl`	The Power of Localization for Efficiently Learning Linear Separators with Malicious Noise. CoRR Pranjal Awasthi, Maria-Florina Balcan, Philip M. Long
2012	J	`jnl`	Active and passive learning of linear separators under log-concave distributions CoRR Maria-Florina Balcan, Philip M. Long
2012	J	`jnl`	Linear classifiers are nearly optimal when hidden variables have diverse effects. Mach. Learn. Nader H. Bshouty, Philip M. Long
2012	A*	`conf`	New Bounds for Learning Intervals with Implications for Semi-Supervised Learning. COLT David P. Helmbold, Philip M. Long
2012	J	`jnl`	On the Necessity of Irrelevant Variables CoRR David P. Helmbold, Philip M. Long
2012	J	`jnl`	On the necessity of irrelevant variables. J. Mach. Learn. Res. David P. Helmbold, Philip M. Long
2011	—	`conf`	Algorithms and hardness results for parallel large margin learning. NIPS Rocco A. Servedio, Philip M. Long
2011	—	`conf`	Learning large-margin halfspaces with more malicious noise. NIPS Philip M. Long, Rocco A. Servedio
2011	A*	`conf`	On the Necessity of Irrelevant Variables. ICML David P. Helmbold, Philip M. Long
2010	A*	`conf`	Finding Planted Partitions in Nearly Linear Time using Arrested Spectral Clustering. ICML Nader H. Bshouty, Philip M. Long
2010	J	`jnl`	Random classification noise defeats all convex potential boosters. Mach. Learn. Philip M. Long, Rocco A. Servedio
2010	A*	`conf`	Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate. ICML Philip M. Long, Rocco A. Servedio
2009	—	`conf`	Baum's Algorithm Learns Intersections of Halfspaces with Respect to Log-Concave Distributions. APPROX-RANDOM Adam R. Klivans, Philip M. Long, Alex K. Tang
2009	—	`conf`	Learning Halfspaces with Malicious Noise. ICALP (1) Adam R. Klivans, Philip M. Long, Rocco A. Servedio
2009	J	`jnl`	Learning Halfspaces with Malicious Noise. J. Mach. Learn. Res. Adam R. Klivans, Philip M. Long, Rocco A. Servedio
2009	A*	`conf`	Linear Classifiers are Nearly Optimal When Hidden Variables Have Diverse Effect. COLT Nader H. Bshouty, Philip M. Long
2009	J	`jnl`	Using the doubling dimension to analyze the generalization of learning algorithms. J. Comput. Syst. Sci. Nader H. Bshouty, Yi Li, Philip M. Long
2008	—	`conf`	Adaptive Martingale Boosting. NIPS Philip M. Long, Rocco A. Servedio
2008	J	`jnl`	Guest editors' introduction: Special issue on learning theory. J. Comput. Syst. Sci. Peter Auer, Philip M. Long
2008	J	`jnl`	Preface. Theor. Comput. Sci. Philip M. Long, Frank Stephan
2008	A*	`conf`	Random classification noise defeats all convex potential boosters. ICML Philip M. Long, Rocco A. Servedio
2007	—	`conf`	Boosting the Area under the ROC Curve. NIPS Philip M. Long, Rocco A. Servedio
2007	J	`jnl`	Discriminative learning can succeed where generative learning fails. Inf. Process. Lett. Philip M. Long, Rocco A. Servedio, Hans Ulrich Simon
2007	—	`conf`	One-Pass Boosting. NIPS Zafer Barutçuoglu, Philip M. Long, Rocco A. Servedio
2007	J	`jnl`	Online Learning of Multiple Tasks with a Shared Loss. J. Mach. Learn. Res. Ofer Dekel, Philip M. Long, Yoram Singer
2006	B	`ed.`	Algorithmic Learning Theory, 17th International Conference, ALT 2006, Barcelona, Spain, October 7-10, 2006, Proceedings ALT José L. Balcázar, Philip M. Long, Frank Stephan
2006	—	`conf`	Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions. NIPS Philip M. Long, Rocco A. Servedio
2006	A*	`conf`	Discriminative Learning Can Succeed Where Generative Learning Fails. COLT Philip M. Long, Rocco A. Servedio
2006	B	`conf`	Editors' Introduction. ALT José L. Balcázar, Philip M. Long, Frank Stephan
2006	—	`conf`	Learnability and the doubling dimension. NIPS Yi Li, Philip M. Long
2006	A*	`conf`	Online Multitask Learning. COLT Ofer Dekel, Philip M. Long, Yoram Singer
2006	A*	`conf`	Predicting Electricity Distribution Feeder Failures Using Machine Learning Susceptibility Analysis. AAAI Philip Gross, Albert Boulanger, Marta Arias, David L. Waltz, Philip M. Long, Charles Lawson, Roger Anderson, Matthew Koenig, Mark Mastrocinque, William Fairechio, John A. Johnson, Serena Lee, Frank Doherty, Arthur Kressner
2005	A*	`conf`	Martingale Boosting. COLT Philip M. Long, Rocco A. Servedio
2005	J	`jnl`	Performance guarantees for hierarchical clustering. J. Comput. Syst. Sci. Sanjoy Dasgupta, Philip M. Long
2005	A*	`conf`	Unsupervised evidence integration. ICML Philip M. Long, Vinay Varadan, Sarah Gilman, Mark Treshock, Rocco A. Servedio
2004	J	`jnl`	Efficient algorithms for learning functions with bounded variation. Inf. Comput. Philip M. Long
2004	—	`conf`	Mistake Bounds for Maximum Entropy Discrimination. NIPS Philip M. Long, Xinyu Wu
2003	J	`jnl`	A Theoretical Analysis of Query Selection for Collaborative Filtering. Mach. Learn. Sanjoy Dasgupta, Wee Sun Lee, Philip M. Long
2003	J	`jnl`	An upper bound on the sample complexity of PAC-learning halfspaces with respect to the uniform distribution. Inf. Process. Lett. Philip M. Long
2003	J	`jnl`	Boosting and Microarray Data. Mach. Learn. Philip M. Long, Vinsensius Berlian Vega SN
2003	A*	`conf`	Boosting with Diverse Base Classifiers. COLT Sanjoy Dasgupta, Philip M. Long
2003	J	`jnl`	On the difficulty of approximately maximizing agreements. J. Comput. Syst. Sci. Shai Ben-David, Nadav Eiron, Philip M. Long
2003	J	`jnl`	Reinforcement Learning with Immediate Rewards and Linear Hypotheses. Algorithmica Naoki Abe, Alan W. Biermann, Philip M. Long
2002	—	`conf`	Minimum Majority Classification and Boosting. AAAI/IAAI Philip M. Long
2002	J	`jnl`	The Relaxed Online Maximum Margin Algorithm. Mach. Learn. Yi Li, Philip M. Long
2001	—	`conf`	A Theoretical Analysis of Query Selection for Collaborative Filtering. COLT/EuroCOLT Wee Sun Lee, Philip M. Long
2001	—	`conf`	Agnostic Boosting. COLT/EuroCOLT Shai Ben-David, Philip M. Long, Yishay Mansour
2001	J	`jnl`	Improved Bounds on the Sample Complexity of Learning. J. Comput. Syst. Sci. Yi Li, Philip M. Long, Aravind Srinivasan
2001	—	`conf`	On Agnostic Learning with {0, *, 1}-Valued and Real-Valued Hypotheses. COLT/EuroCOLT Philip M. Long
2001	J	`jnl`	The one-inclusion graph algorithm is near-optimal for the prediction model of learning. IEEE Trans. Inf. Theory Yi Li, Philip M. Long, Aravind Srinivasan
2001	B	`conf`	Using the Pseudo-Dimension to Analyze Approximation Algorithms for Integer Programming. WADS Philip M. Long
2000	J	`jnl`	Apple Tasting. Inf. Comput. David P. Helmbold, Nick Littlestone, Philip M. Long
2000	J	`jnl`	Approximating Hyper-Rectangles: Learning and Pseudo-random Sets Electron. Colloquium Comput. Complex. Peter Auer, Philip M. Long, Aravind Srinivasan
2000	J	`jnl`	Improved bounds about on-line learning of smooth-functions of a single variable. Theor. Comput. Sci. Philip M. Long
2000	A*	`conf`	Improved bounds on the sample complexity of learning. SODA Yi Li, Philip M. Long, Aravind Srinivasan
2000	J	`jnl`	On the Complexity of Function Learning Electron. Colloquium Comput. Complex. Peter Auer, Philip M. Long, Wolfgang Maass, Gerhard J. Woeginger
2000	A*	`conf`	On the Difficulty of Approximately Maximizing Agreements. COLT Shai Ben-David, Nadav Eiron, Philip M. Long
2000	J	`jnl`	On-Line Learning with Linear Loss Constraints. Inf. Comput. David P. Helmbold, Nick Littlestone, Philip M. Long
2000	J	`jnl`	Simulating Access to Hidden Information while Learning Electron. Colloquium Comput. Complex. Peter Auer, Philip M. Long
1999	J	`jnl`	Adaptive Disk Spindown via Optimal Rent-to-Buy in Probabilistic Environments. Algorithmica P. Krishnan, Philip M. Long, Jeffrey Scott Vitter
1999	A*	`conf`	Associative Reinforcement Learning using Linear Probabilistic Concepts. ICML Naoki Abe, Philip M. Long
1999	J	`jnl`	Dictionary Selection Using Partial Matching. Inf. Sci. Dzung T. Hoang, Philip M. Long, Jeffrey Scott Vitter
1999	A*	`ed.`	Proceedings of the Twelfth Annual Conference on Computational Learning Theory, COLT 1999, Santa Cruz, CA, USA, July 7-9, 1999 COLT Shai Ben-David, Philip M. Long
1999	J	`jnl`	Structural Results About On-line Learning Models With and Without Queries. Mach. Learn. Peter Auer, Philip M. Long
1999	J	`jnl`	Text compression via alphabet re-representation. Neural Networks Philip M. Long, Apostol Natsev, Jeffrey Scott Vitter
1999	J	`jnl`	The Complexity of Learning According to Two Models of a Drifting Environment. Mach. Learn. Philip M. Long
1999	—	`conf`	The Relaxed Online Maximum Margin Algorithm. NIPS Yi Li, Philip M. Long
1998	J	`jnl`	Approximating Hyper-Rectangles: Learning and Pseudorandom Sets. J. Comput. Syst. Sci. Peter Auer, Philip M. Long, Aravind Srinivasan
1998	J	`jnl`	Efficient cost measures for motion estimation at low bit rates. IEEE Trans. Circuits Syst. Video Technol. Dzung T. Hoang, Philip M. Long, Jeffrey Scott Vitter
1998	A*	`conf`	On the Sample Complexity of Learning Functions with Bounded Variation. COLT Philip M. Long
1998	J	`jnl`	PAC Learning Axis-aligned Rectangles with Respect to Product Distributions from Multiple-Instance Examples. Mach. Learn. Philip M. Long, Lei Tan
1998	J	`jnl`	Prediction, Learning, Uniform Convergence, and Scale-Sensitive Dimensions. J. Comput. Syst. Sci. Peter L. Bartlett, Philip M. Long
1998	A*	`conf`	The complexity of learning according to two models of a drifting environment. COLT Philip M. Long
1997	A*	`conf`	Approximating Hyper-Rectangles: Learning and Pseudo-Random Sets. STOC Peter Auer, Philip M. Long, Aravind Srinivasan
1997	J	`jnl`	Guest Editor's Introduction. Mach. Learn. Philip M. Long
1997	J	`jnl`	On the Complexity of Learning from Drifting Distributions. Inf. Comput. Rakesh D. Barve, Philip M. Long
1997	A*	`conf`	On-line Evaluation and Prediction using Linear Functions. COLT Philip M. Long
1997	B	`conf`	Text Compression Via Alphabet Re-Representation. Data Compression Conference Philip M. Long, Apostol Natsev, Jeffrey Scott Vitter
1996	B	`conf`	Efficient Cost Measures for Motion Compensation at Low Bit Rates (Extended Abstract). Data Compression Conference Dzung T. Hoang, Philip M. Long, Jeffrey Scott Vitter
1996	J	`jnl`	Fat-Shattering and the Learnability of Real-Valued Functions. J. Comput. Syst. Sci. Peter L. Bartlett, Philip M. Long, Robert C. Williamson
1996	B	`conf`	Improved Bounds about On-line Learning of Smooth Functions of a Single Variable. ALT Philip M. Long
1996	A*	`conf`	On the Complexity of Learning from Drifting Distributions. COLT Rakesh D. Barve, Philip M. Long
1996	A*	`conf`	PAC Learning Axis-Aligned Rectangles with Respect to Product Distributions from Multiple-Instance Examples. COLT Philip M. Long, Lei Tan
1996	J	`jnl`	Worst-case quadratic loss bounds for prediction using linear functions and gradient descent. IEEE Trans. Neural Networks Nicolò Cesa-Bianchi, Philip M. Long, Manfred K. Warmuth
1995	J	`jnl`	A Generalization of Sauer's Lemma. J. Comb. Theory A David Haussler, Philip M. Long
1995	J	`jnl`	Characterizations of Learnability for Classes of {0, ..., n}-Valued Functions. J. Comput. Syst. Sci. Shai Ben-David, Nicolò Cesa-Bianchi, David Haussler, Philip M. Long
1995	A*	`conf`	Learning to Make Rent-to-Buy Decisions with Systems Applications. ICML P. Krishnan, Philip M. Long, Jeffrey Scott Vitter
1995	A*	`conf`	More Theorems about Scale-sensitive Dimensions and Learning. COLT Peter L. Bartlett, Philip M. Long
1995	B	`conf`	Multiple-Dictionary Coding Using Partial Matching. Data Compression Conference Dzung T. Hoang, Philip M. Long, Jeffrey Scott Vitter
1995	J	`jnl`	On the Complexity of Function Learning. Mach. Learn. Peter Auer, Philip M. Long, Wolfgang Maass, Gerhard J. Woeginger
1995	J	`jnl`	On the sample complexity of PAC learning half-spaces against the uniform distribution. IEEE Trans. Neural Networks Philip M. Long
1995	J	`jnl`	On-Line Learning of Smooth Functions of a Single Variable. Theor. Comput. Sci. Don Kimber, Philip M. Long
1995	J	`jnl`	On-line Learning of Linear Functions. Comput. Complex. Nick Littlestone, Philip M. Long, Manfred K. Warmuth
1994	J	`jnl`	Composite Geometric Concepts and Polynomial Predictability Inf. Comput. Philip M. Long, Manfred K. Warmuth
1994	B	`conf`	Explicit Bit Minimization for Motion-Compensated Video Coding. Data Compression Conference Dzung T. Hoang, Philip M. Long, Jeffrey Scott Vitter
1994	A*	`conf`	Fat-Shattering and the Learnability of Real-Valued Functions. COLT Peter L. Bartlett, Philip M. Long, Robert C. Williamson
1994	J	`jnl`	Halfspace Learning, Linear Programming, and Nonmalicious Distributions. Inf. Process. Lett. Philip M. Long
1994	A*	`conf`	Simulating access to hidden information while learning. STOC Peter Auer, Philip M. Long
1994	J	`jnl`	Tracking Drifting Concepts By Minimizing Disagreements. Mach. Learn. David P. Helmbold, Philip M. Long
1993	A*	`conf`	On the Complexity of Function Learning. COLT Peter Auer, Philip M. Long, Wolfgang Maass, Gerhard J. Woeginger
1993	A*	`conf`	On-Line Learning with Linear Loss Constraints. COLT Nick Littlestone, Philip M. Long
1993	A*	`conf`	Worst-Case Quadratic Loss Bounds for a Generalization of the Widrow-Hoff Rule. COLT Nicolò Cesa-Bianchi, Philip M. Long, Manfred K. Warmuth
1992	A*	`conf`	Apple Tasting and Nearly One-Sided Learning FOCS David P. Helmbold, Nick Littlestone, Philip M. Long
1992	A*	`conf`	Characterizations of Learnability for Classes of { COLT Shai Ben-David, Nicolò Cesa-Bianchi, Philip M. Long
1992	A*	`conf`	The Learning Complexity of Smooth Functions of a Single Variable. COLT Don Kimber, Philip M. Long
1991	A*	`conf`	On-Line Learning of Linear Functions STOC Nick Littlestone, Philip M. Long, Manfred K. Warmuth
1991	A*	`conf`	Tracking Drifting Concepts Using Random Examples. COLT David P. Helmbold, Philip M. Long
1990	A*	`conf`	Composite Geometric Concepts and Polynomial Predictability. COLT Philip M. Long, Manfred K. Warmuth