Manfred K. Warmuth

250 papers A* 80A 10B 15C 1Misc 1Journal 111Unranked 32

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Hard labels sampled from sparse targets mislead rotation invariant algorithms. CoRR Avrajit Ghosh, Bin Yu, Manfred K. Warmuth, Peter L. Bartlett
2025	B	`conf`	How rotation invariant algorithms are fooled by noise on sparse targets. ALT Manfred K. Warmuth, Wojciech Kotlowski, Matt Jones, Ehsan Amid
2025	J	`jnl`	Selective Matching Losses - Not All Scores Are Created Equal. CoRR Gil I. Shamir, Manfred K. Warmuth
2024	B	`conf`	A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks. ALT Jacob D. Abernethy, Alekh Agarwal, Teodor Vanislavov Marinov, Manfred K. Warmuth
2024	A*	`conf`	Hyperbolic Embeddings of Supervised Models. NeurIPS Richard Nock, Ehsan Amid, Frank Nielsen, Alexander Soen, Manfred K. Warmuth
2024	J	`jnl`	Noise misleads rotation invariant algorithms on sparse targets. CoRR Manfred K. Warmuth, Wojciech Kotlowski, Matt Jones, Ehsan Amid
2024	A*	`conf`	Optimal Transport with Tempered Exponential Measures. AAAI Ehsan Amid, Frank Nielsen, Richard Nock, Manfred K. Warmuth
2024	J	`jnl`	Tempered Calculus for ML: Application to Hyperbolic Model Embedding. CoRR Richard Nock, Ehsan Amid, Frank Nielsen, Alexander Soen, Manfred K. Warmuth
2023	J	`jnl`	A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks. CoRR Jacob D. Abernethy, Alekh Agarwal, Teodor V. Marinov, Manfred K. Warmuth
2023	A*	`conf`	Boosting with Tempered Exponential Measures. NeurIPS Richard Nock, Ehsan Amid, Manfred K. Warmuth
2023	J	`jnl`	Boosting with Tempered Exponential Measures. CoRR Richard Nock, Ehsan Amid, Manfred K. Warmuth
2023	A	`conf`	Clustering above Exponential Families with Tempered Exponential Measures. AISTATS Ehsan Amid, Richard Nock, Manfred K. Warmuth
2023	J	`jnl`	Layerwise Bregman Representation Learning of Neural Networks with Applications to Knowledge Distillation. Trans. Mach. Learn. Res. Ehsan Amid, Rohan Anil, Christopher Fifty, Manfred K. Warmuth
2023	A*	`conf`	Open Problem: Learning sparse linear concepts by priming the features. COLT Manfred K. Warmuth, Ehsan Amid
2023	J	`jnl`	Optimal Transport with Tempered Exponential Measures. CoRR Ehsan Amid, Frank Nielsen, Richard Nock, Manfred K. Warmuth
2023	J	`jnl`	The Tempered Hilbert Simplex Distance and Its Application To Non-linear Embeddings of TEMs. CoRR Ehsan Amid, Frank Nielsen, Richard Nock, Manfred K. Warmuth
2022	J	`jnl`	Clustering above Exponential Families with Tempered Exponential Measures. CoRR Ehsan Amid, Richard Nock, Manfred K. Warmuth
2022	J	`jnl`	Layerwise Bregman Representation Learning with Applications to Knowledge Distillation. CoRR Ehsan Amid, Rohan Anil, Christopher Fifty, Manfred K. Warmuth
2022	J	`jnl`	Learning from Randomly Initialized Neural Network Features. CoRR Ehsan Amid, Rohan Anil, Wojciech Kotlowski, Manfred K. Warmuth
2022	A	`conf`	LocoProp: Enhancing BackProp via Local Loss Optimization. AISTATS Ehsan Amid, Rohan Anil, Manfred K. Warmuth
2022	J	`jnl`	Step-size Adaptation Using Exponentiated Gradient Updates. CoRR Ehsan Amid, Rohan Anil, Christopher Fifty, Manfred K. Warmuth
2022	J	`jnl`	Unbiased estimators for random design regression. J. Mach. Learn. Res. Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2022	J	`jnl`	Unlabeled sample compression schemes and corner peelings for ample and maximum classes. J. Comput. Syst. Sci. Jérémie Chalopin, Victor Chepoi, Shay Moran, Manfred K. Warmuth
2021	B	`conf`	A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer. ALT Manfred K. Warmuth, Wojciech Kotlowski, Ehsan Amid
2021	J	`jnl`	Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond. CoRR Negin Majidi, Ehsan Amid, Hossein Talebi, Manfred K. Warmuth
2021	J	`jnl`	LocoProp: Enhancing BackProp via Local Loss Optimization. CoRR Ehsan Amid, Rohan Anil, Manfred K. Warmuth
2020	J	`jnl`	A case where a spindly two-layer linear network whips any neural network with a fully connected input layer. CoRR Manfred K. Warmuth, Wojciech Kotlowski, Ehsan Amid
2020	A*	`conf`	An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint. AAAI Ehsan Amid, Manfred K. Warmuth
2020	A	`conf`	Divergence-Based Motivation for Online EM and Combining Hidden Variable Models. UAI Ehsan Amid, Manfred K. Warmuth
2020	J	`jnl`	Interpolating Between Gradient Descent and Exponentiated Gradient Using Reparameterized Gradient Descent. CoRR Ehsan Amid, Manfred K. Warmuth
2020	B	`conf`	Rank-Smoothed Pairwise Learning In Perceptual Quality Assessment. ICIP Hossein Talebi, Ehsan Amid, Peyman Milanfar, Manfred K. Warmuth
2020	J	`jnl`	Rank-smoothed Pairwise Learning In Perceptual Quality Assessment. CoRR Hossein Talebi, Ehsan Amid, Peyman Milanfar, Manfred K. Warmuth
2020	A*	`conf`	Reparameterizing Mirror Descent as Gradient Descent. NeurIPS Ehsan Amid, Manfred K. Warmuth
2020	A*	`conf`	Winnowing with Gradient Descent. COLT Ehsan Amid, Manfred K. Warmuth
2019	A*	`conf`	Adaptive Scale-Invariant Online Algorithms for Learning Linear Models. ICML Michal Kempka, Wojciech Kotlowski, Manfred K. Warmuth
2019	J	`jnl`	Adaptive scale-invariant online algorithms for learning linear models. CoRR Michal Kempka, Wojciech Kotlowski, Manfred K. Warmuth
2019	J	`jnl`	An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint. CoRR Ehsan Amid, Manfred K. Warmuth
2019	A	`conf`	Correcting the bias in least squares regression with volume-rescaled sampling. AISTATS Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2019	J	`jnl`	Divergence-Based Motivation for Online EM and Combining Hidden Variable Models. CoRR Ehsan Amid, Manfred K. Warmuth
2019	A*	`conf`	Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. COLT Michal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth
2019	J	`jnl`	Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. CoRR Michal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth
2019	J	`jnl`	Mistake bounds on the noise-free multi-armed bandit game. Inf. Comput. Atsuyoshi Nakamura, David P. Helmbold, Manfred K. Warmuth
2019	B	`conf`	Online Non-Additive Path Learning under Full and Partial Information. ALT Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Holakou Rahmanian, Manfred K. Warmuth
2019	A*	`conf`	Robust Bi-Tempered Logistic Loss Based on Bregman Divergences. NeurIPS Ehsan Amid, Manfred K. Warmuth, Rohan Anil, Tomer Koren
2019	J	`jnl`	Robust Bi-Tempered Logistic Loss Based on Bregman Divergences. CoRR Ehsan Amid, Manfred K. Warmuth, Rohan Anil, Tomer Koren
2019	J	`jnl`	TriMap: Large-scale Dimensionality Reduction Using Triplets. CoRR Ehsan Amid, Manfred K. Warmuth
2019	A	`conf`	Two-temperature logistic regression based on the Tsallis divergence. AISTATS Ehsan Amid, Manfred K. Warmuth, Sriram Srinivasan
2019	J	`jnl`	Unbiased estimators for random design regression. CoRR Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2019	A*	`conf`	Unlabeled Sample Compression Schemes and Corner Peelings for Ample and Maximum Classes. ICALP Jérémie Chalopin, Victor Chepoi, Shay Moran, Manfred K. Warmuth
2018	J	`jnl`	A more globally accurate dimensionality reduction method using triplets. CoRR Ehsan Amid, Manfred K. Warmuth
2018	J	`jnl`	Correcting the bias in least squares regression with volume-rescaled sampling. CoRR Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2018	A*	`conf`	Leveraged volume sampling for linear regression. NeurIPS Michal Derezinski, Manfred K. Warmuth, Daniel J. Hsu
2018	J	`jnl`	Online Non-Additive Path Learning under Full and Partial Information. CoRR Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Holakou Rahmanian, Manfred K. Warmuth
2018	J	`jnl`	Reverse Iterative Volume Sampling for Linear Regression. J. Mach. Learn. Res. Michal Derezinski, Manfred K. Warmuth
2018	J	`jnl`	Reverse iterative volume sampling for linear regression. CoRR Michal Derezinski, Manfred K. Warmuth
2018	J	`jnl`	Speech Recognition: Keyword Spotting Through Image Recognition. CoRR Sanjay Krishna Gouda, Salil Kanetkar, David Harrison, Manfred K. Warmuth
2018	A	`conf`	Subsampling for Ridge Regression via Regularized Volume Sampling. AISTATS Michal Derezinski, Manfred K. Warmuth
2018	J	`jnl`	Tail bounds for volume sampled linear regression. CoRR Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2018	J	`jnl`	Unlabeled sample compression schemes and corner peelings for ample and maximum classes. CoRR Jérémie Chalopin, Victor Chepoi, Shay Moran, Manfred K. Warmuth
2017	—	`conf`	Online Dynamic Programming. NIPS Holakou Rahmanian, Manfred K. Warmuth
2017	J	`jnl`	Online Dynamic Programming. CoRR Holakou Rahmanian, S. V. N. Vishwanathan, Manfred K. Warmuth
2017	J	`jnl`	Subsampling for Ridge Regression via Regularized Volume Sampling. CoRR Michal Derezinski, Manfred K. Warmuth
2017	J	`jnl`	Two-temperature logistic regression based on the Tsallis divergence. CoRR Ehsan Amid, Manfred K. Warmuth
2017	—	`conf`	Unbiased estimates for linear regression via volume sampling. NIPS Michal Derezinski, Manfred K. Warmuth
2017	J	`jnl`	Unbiased estimates for linear regression via volume sampling. CoRR Michal Derezinski, Manfred K. Warmuth
2016	B	`conf`	Labeled Compression Schemes for Extremal Classes. ALT Shay Moran, Manfred K. Warmuth
2016	J	`jnl`	Learning rotations with little regret. Mach. Learn. Elad Hazan, Satyen Kale, Manfred K. Warmuth
2016	C	`conf`	Noise Free Multi-armed Bandit Game. LATA Atsuyoshi Nakamura, David P. Helmbold, Manfred K. Warmuth
2016	J	`jnl`	Online PCA with Optimal Regret. J. Mach. Learn. Res. Jiazhong Nie, Wojciech Kotlowski, Manfred K. Warmuth
2016	J	`jnl`	t-Exponential Triplet Embedding. CoRR Ehsan Amid, Nikos Vlassis, Manfred K. Warmuth
2015	J	`jnl`	Labeled compression schemes for extremal classes. CoRR Shay Moran, Manfred K. Warmuth
2015	A*	`conf`	Minimax Fixed-Design Linear Regression. COLT Peter L. Bartlett, Wouter M. Koolen, Alan Malek, Eiji Takimoto, Manfred K. Warmuth
2015	A*	`conf`	On-Line Learning Algorithms for Path Experts with Non-Additive Losses. COLT Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Manfred K. Warmuth
2015	A*	`conf`	Open Problem: Online Sabotaged Shortest Path. COLT Wouter M. Koolen, Manfred K. Warmuth, Dmitry Adamskiy
2015	J	`jnl`	PCA with Gaussian perturbations. CoRR Wojciech Kotlowski, Manfred K. Warmuth
2014	J	`jnl`	A Bayesian Probability Calculus for Density Matrices. CoRR Manfred K. Warmuth, Dima Kuzmin
2014	J	`jnl`	Combining initial segments of lists. Theor. Comput. Sci. Manfred K. Warmuth, Wouter M. Koolen, David P. Helmbold
2014	J	`jnl`	Kernelization of matrix updates, when and how? Theor. Comput. Sci. Manfred K. Warmuth, Wojciech Kotlowski, Shuisheng Zhou
2014	A*	`conf`	Open Problem: Shifting Experts on Easy Data. COLT Manfred K. Warmuth, Wouter M. Koolen
2014	—	`conf`	The limits of squared Euclidean distance regularization. NIPS Michal Derezinski, Manfred K. Warmuth
2013	A*	`conf`	Learning a set of directions. COLT Wouter M. Koolen, Jiazhong Nie, Manfred K. Warmuth
2013	J	`jnl`	On-line PCA with Optimal Regrets. CoRR Jiazhong Nie, Wojciech Kotlowski, Manfred K. Warmuth
2013	B	`conf`	Online PCA with Optimal Regrets. ALT Jiazhong Nie, Wojciech Kotlowski, Manfred K. Warmuth
2013	A*	`conf`	Open Problem: Lower bounds for Boosting with Hadamard Matrices. COLT Jiazhong Nie, Manfred K. Warmuth, S. V. N. Vishwanathan, Xinhua Zhang
2013	J	`jnl`	Relative Loss Bounds for On-line Density Estimation with the Exponential Family of Distributions CoRR Katy S. Azoury, Manfred K. Warmuth
2012	B	`conf`	Kernelization of Matrix Updates, When and How? ALT Manfred K. Warmuth, Wojciech Kotlowski, Shuisheng Zhou
2012	J	`jnl`	Online variance minimization. Mach. Learn. Manfred K. Warmuth, Dima Kuzmin
2012	—	`conf`	Putting Bayes to sleep. NIPS Wouter M. Koolen, Dmitry Adamskiy, Manfred K. Warmuth
2011	B	`conf`	Combining Initial Segments of Lists. ALT Manfred K. Warmuth, Wouter M. Koolen, David P. Helmbold
2011	—	`conf`	Learning Eigenvectors for Free. NIPS Wouter M. Koolen, Wojciech Kotlowski, Manfred K. Warmuth
2011	A*	`conf`	Minimax Algorithm for Learning Rotations. COLT Wojciech Kotlowski, Manfred K. Warmuth
2010	J	`jnl`	Bayesian generalized probability calculus for density matrices. Mach. Learn. Manfred K. Warmuth, Dima Kuzmin
2010	A*	`conf`	Hedging Structured Concepts. COLT Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivinen
2010	A*	`conf`	Learning Rotations with Little Regret. COLT Elad Hazan, Satyen Kale, Manfred K. Warmuth
2010	Misc	`conf`	New combination coefficients for AdaBoost algorithms. ICNC Shuisheng Zhou, Manfred K. Warmuth, Yinli Dong, Feng Ye
2010	A*	`conf`	On-line Variance Minimization in O(n2) per Trial? COLT Elad Hazan, Satyen Kale, Manfred K. Warmuth
2010	—	`conf`	Repeated Games against Budgeted Adversaries. NIPS Jacob D. Abernethy, Manfred K. Warmuth
2010	B	`conf`	The Blessing and the Curse of the Multiplicative Updates. ALT Manfred K. Warmuth
2010	B	`conf`	The Blessing and the Curse of the Multiplicative Updates. Discovery Science Manfred K. Warmuth
2009	J	`jnl`	Learning Permutations with Exponential Weights. J. Mach. Learn. Res. David P. Helmbold, Manfred K. Warmuth
2009	A*	`conf`	Minimax Games with Bandits. COLT Jacob D. Abernethy, Manfred K. Warmuth
2009	A*	`conf`	Tutorial summary: Survey of boosting from an optimization perspective. ICML Manfred K. Warmuth, S. V. N. Vishwanathan
2008	B	`conf`	Entropy Regularized LPBoost. ALT Manfred K. Warmuth, Karen A. Glocer, S. V. N. Vishwanathan
2008	A*	`conf`	Learning Rotations. COLT Adam M. Smith, Manfred K. Warmuth
2008	A*	`conf`	When Random Play is Optimal Against an Adversary. COLT Jacob D. Abernethy, Manfred K. Warmuth, Joel Yellin
2007	—	`conf`	Boosting Algorithms for Maximizing the Soft Margin. NIPS Manfred K. Warmuth, Karen A. Glocer, Gunnar Rätsch
2007	A*	`conf`	Learning Permutations with Exponential Weights. COLT David P. Helmbold, Manfred K. Warmuth
2007	A*	`conf`	Online kernel PCA with entropic matrix updates. ICML Dima Kuzmin, Manfred K. Warmuth
2007	J	`jnl`	Unlabeled Compression Schemes for Maximum Classes. J. Mach. Learn. Res. Dima Kuzmin, Manfred K. Warmuth
2007	A*	`conf`	When Is There a Free Matrix Lunch? COLT Manfred K. Warmuth
2007	A*	`conf`	Winnowing subspaces. ICML Manfred K. Warmuth
2006	A	`conf`	A Bayesian Probability Calculus for Density Matrices. UAI Manfred K. Warmuth, Dima Kuzmin
2006	A*	`conf`	Can Entropic Regularization Be Replaced by Squared Euclidean Distance Plus Additional Linear Constraints. COLT Manfred K. Warmuth
2006	A*	`conf`	Continuous Experts and the Binning Algorithm. COLT Jacob D. Abernethy, John Langford, Manfred K. Warmuth
2006	A*	`conf`	Online Variance Minimization. COLT Manfred K. Warmuth, Dima Kuzmin
2006	—	`conf`	Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension. NIPS Manfred K. Warmuth, Dima Kuzmin
2006	J	`jnl`	The p-norm generalization of the LMS algorithm for adaptive filtering. IEEE Trans. Signal Process. Jyrki Kivinen, Manfred K. Warmuth, Babak Hassibi
2006	A*	`conf`	Totally corrective boosting algorithms that maximize the margin. ICML Manfred K. Warmuth, Jun Liao, Gunnar Rätsch
2005	—	`conf`	A Bayes Rule for Density Matrices. NIPS Manfred K. Warmuth
2005	J	`jnl`	Efficient Margin Maximizing with Boosting. J. Mach. Learn. Res. Gunnar Rätsch, Manfred K. Warmuth
2005	A*	`conf`	Leaving the Span. COLT Manfred K. Warmuth, S. V. N. Vishwanathan
2005	J	`jnl`	Matrix Exponentiated Gradient Updates for On-line Learning and Bregman Projection. J. Mach. Learn. Res. Koji Tsuda, Gunnar Rätsch, Manfred K. Warmuth
2005	A*	`conf`	Optimum Follow the Leader Algorithm. COLT Dima Kuzmin, Manfred K. Warmuth
2005	A*	`conf`	Unlabeled Compression Schemes for Maximum Classes, . COLT Dima Kuzmin, Manfred K. Warmuth
2004	—	`conf`	Matrix Exponential Gradient Updates for On-line Learning and Bregman Projection. NIPS Koji Tsuda, Gunnar Rätsch, Manfred K. Warmuth
2004	A*	`conf`	The Optimal PAC Algorithm. COLT Manfred K. Warmuth
2003	J	`jnl`	Active Learning with Support Vector Machines in the Drug Discovery Process. J. Chem. Inf. Comput. Sci. Manfred K. Warmuth, Jun Liao, Gunnar Rätsch, Michael Mathieson, Santosh Putta, Christian Lemmen
2003	—	`conf`	Boosting versus Covering. NIPS Kohei Hatano, Manfred K. Warmuth
2003	A	`conf`	Classification with free energy at raised temperatures. INTERSPEECH Rita Singh, Manfred K. Warmuth, Bhiksha Raj, Paul Lamere
2003	A*	`conf`	Compressing to VC Dimension Many Points. COLT Manfred K. Warmuth
2003	A*	`ed.`	Computational Learning Theory and Kernel Machines, 16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington, DC, USA, August 24-27, 2003, Proceedings COLT Bernhard Schölkopf, Manfred K. Warmuth
2003	A	`conf`	Inline updates for HMMs. INTERSPEECH Ashutosh Garg, Manfred K. Warmuth
2003	J	`jnl`	Path Kernels and Multiplicative Updates. J. Mach. Learn. Res. Eiji Takimoto, Manfred K. Warmuth
2003	J	`jnl`	Relative Loss Bounds for Temporal-Difference Learning. Mach. Learn. Jürgen Forster, Manfred K. Warmuth
2002	—	`conf`	Adaptive Caching by Refetching. NIPS Robert B. Gramacy, Manfred K. Warmuth, Scott A. Brandt, Ismail Ari
2002	J	`jnl`	Direct and indirect algorithms for on-line learning of disjunctions. Theor. Comput. Sci. David P. Helmbold, Sandra Panizza, Manfred K. Warmuth
2002	A*	`conf`	Maximizing the Margin with Boosting. COLT Gunnar Rätsch, Manfred K. Warmuth
2002	A*	`conf`	Path Kernels and Multiplicative Updates. COLT Eiji Takimoto, Manfred K. Warmuth
2002	J	`jnl`	Predicting nearly as well as the best pruning of a planar decision graph. Theor. Comput. Sci. Eiji Takimoto, Manfred K. Warmuth
2002	J	`jnl`	Relative Expected Instantaneous Loss Bounds. J. Comput. Syst. Sci. Jürgen Forster, Manfred K. Warmuth
2002	J	`jnl`	Tracking a Small Set of Experts by Mixing Past Posteriors. J. Mach. Learn. Res. Olivier Bousquet, Manfred K. Warmuth
2001	—	`conf`	Active Learning in the Drug Discovery Process. NIPS Manfred K. Warmuth, Gunnar Rätsch, Michael Mathieson, Jun Liao, Christian Lemmen
2001	—	`conf`	On the Convergence of Leveraging. NIPS Gunnar Rätsch, Sebastian Mika, Manfred K. Warmuth
2001	J	`jnl`	Relative Loss Bounds for Multidimensional Regression Problems. Mach. Learn. Jyrki Kivinen, Manfred K. Warmuth
2001	J	`jnl`	Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions. Mach. Learn. Katy S. Azoury, Manfred K. Warmuth
2001	—	`conf`	Tracking a Small Set of Experts by Mixing Past Posteriors. COLT/EuroCOLT Olivier Bousquet, Manfred K. Warmuth
2001	J	`jnl`	Tracking the Best Linear Predictor. J. Mach. Learn. Res. Mark Herbster, Manfred K. Warmuth
2000	A*	`conf`	Barrier Boosting. COLT Gunnar Rätsch, Manfred K. Warmuth, Sebastian Mika, Takashi Onoda, Steven Lemm, Klaus-Robert Müller
2000	J	`jnl`	Learning of Depth Two Neural Networks with Constant Fan-in at the Hidden Nodes Electron. Colloquium Comput. Complex. Peter Auer, Stephen Kwek, Wolfgang Maass, Manfred K. Warmuth
2000	A*	`conf`	Relative Expected Instantaneous Loss Bounds. COLT Jürgen Forster, Manfred K. Warmuth
2000	A*	`conf`	Relative Loss Bounds for Temporal-Difference Learning. ICML Jürgen Forster, Manfred K. Warmuth
2000	B	`conf`	The Last-Step Minimax Algorithm. ALT Eiji Takimoto, Manfred K. Warmuth
2000	A*	`conf`	The Minimax Strategy for Gaussian Density Estimation. pp. COLT Eiji Takimoto, Manfred K. Warmuth
2000	J	`jnl`	Tracking the best disjunction Electron. Colloquium Comput. Complex. Peter Auer, Manfred K. Warmuth
1999	—	`conf`	Averaging Expert Predictions EuroCOLT Jyrki Kivinen, Manfred K. Warmuth
1999	A*	`conf`	Boosting as Entropy Projection. COLT Jyrki Kivinen, Manfred K. Warmuth
1999	—	`conf`	Direct and Indirect Algorithms for On-line Learning of Disjunctions. EuroCOLT David P. Helmbold, Sandra Panizza, Manfred K. Warmuth
1999	B	`conf`	Predicting Nearly as well as the best Pruning of a Planar Decision Graph. ALT Eiji Takimoto, Manfred K. Warmuth
1999	A	`conf`	Relative Loss Bounds for On-line Density Estirnation with the Exponential Family of Distributions. UAI Katy S. Azoury, Manfred K. Warmuth
1999	J	`jnl`	Relative loss bounds for single neurons. IEEE Trans. Neural Networks David P. Helmbold, Jyrki Kivinen, Manfred K. Warmuth
1998	—	`conf`	Batch and On-Line Parameter Estimation of Gaussian Mixtures Based on the Joint Entropy. NIPS Yoram Singer, Manfred K. Warmuth
1998	J	`jnl`	Efficient Learning With Virtual Threshold Gates. Inf. Comput. Wolfgang Maass, Manfred K. Warmuth
1998	—	`conf`	Linear Hinge Loss and Average Margin. NIPS Claudio Gentile, Manfred K. Warmuth
1998	J	`jnl`	Sequential Prediction of Individual Sequences Under General Loss Functions. IEEE Trans. Inf. Theory David Haussler, Jyrki Kivinen, Manfred K. Warmuth
1998	J	`jnl`	Tracking the Best Disjunction. Mach. Learn. Peter Auer, Manfred K. Warmuth
1998	J	`jnl`	Tracking the Best Expert. Mach. Learn. Mark Herbster, Manfred K. Warmuth
1998	A*	`conf`	Tracking the Best Regressor. COLT Mark Herbster, Manfred K. Warmuth
1997	J	`jnl`	A Comparison of New and Old Algorithms for a Mixture Estimation Problem. Mach. Learn. David P. Helmbold, Robert E. Schapire, Yoram Singer, Manfred K. Warmuth
1997	J	`jnl`	Exponentiated Gradient Versus Gradient Descent for Linear Predictors. Inf. Comput. Jyrki Kivinen, Manfred K. Warmuth
1997	J	`jnl`	How to use expert advice. J. ACM Nicolò Cesa-Bianchi, Yoav Freund, David Haussler, David P. Helmbold, Robert E. Schapire, Manfred K. Warmuth
1997	—	`conf`	Relative Loss Bounds for Multidimensional Regression Problems. NIPS Jyrki Kivinen, Manfred K. Warmuth
1997	—	`conf`	Relative Loss Bounds, the Minimum Relative Entropy Principle, and EM. NIPS Manfred K. Warmuth
1997	—	`conf`	Sample Compression, Learnability, and the Vapnik-Chervonenkis Dimension. EuroCOLT Manfred K. Warmuth
1997	J	`jnl`	The Perceptron Algorithm Versus Winnow: Linear Versus Logarithmic Mistake Bounds when Few Input Variables are Relevant (Technical Note). Artif. Intell. Jyrki Kivinen, Manfred K. Warmuth, Peter Auer
1997	A*	`conf`	Using and Combining Predictors That Specialize. STOC Yoav Freund, Robert E. Schapire, Yoram Singer, Manfred K. Warmuth
1996	A*	`conf`	Learning of Depth Two Neural Networks with Constant Fan-In at the Hidden Nodes (Extended Abstract). COLT Peter Auer, Stephen Kwek, Wolfgang Maass, Manfred K. Warmuth
1996	J	`jnl`	On the Worst-Case Analysis of Temporal-Difference Learning Algorithms. Mach. Learn. Robert E. Schapire, Manfred K. Warmuth
1996	A*	`conf`	On-Line Portfolio Selection Using Multiplicative Updates. ICML David P. Helmbold, Robert E. Schapire, Yoram Singer, Manfred K. Warmuth
1996	J	`jnl`	On-line Prediction and Conversion Strategies. Mach. Learn. Nicolò Cesa-Bianchi, Yoav Freund, David P. Helmbold, Manfred K. Warmuth
1996	—	`conf`	Training Algorithms for Hidden Markov Models using Entropy Based Distance Functions. NIPS Yoram Singer, Manfred K. Warmuth
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	A*	`conf`	A Comparison of New and Old Algorithms for a Mixture Estimation Problem. COLT David P. Helmbold, Yoram Singer, Robert E. Schapire, Manfred K. Warmuth
1995	A*	`conf`	Additive versus exponentiated gradient updates for linear prediction. STOC Jyrki Kivinen, Manfred K. Warmuth
1995	A*	`conf`	Efficient Learning with Virtual Threshold Gates. ICML Wolfgang Maass, Manfred K. Warmuth
1995	—	`conf`	Exponentially many local minima for single neurons. NIPS Peter Auer, Mark Herbster, Manfred K. Warmuth
1995	J	`jnl`	Learning Binary Relations Using Weighted Majority Voting. Mach. Learn. Sally A. Goldman, Manfred K. Warmuth
1995	J	`jnl`	On Weak Learning. J. Comput. Syst. Sci. David P. Helmbold, Manfred K. Warmuth
1995	J	`jnl`	On-line Learning of Linear Functions. Comput. Complex. Nick Littlestone, Philip M. Long, Manfred K. Warmuth
1995	J	`jnl`	Sample Compression, Learnability, and the Vapnik-Chervonenkis Dimension. Mach. Learn. Sally Floyd, Manfred K. Warmuth
1995	A*	`conf`	The Perceptron Algorithm vs. Winnow: Linear vs. Logarithmic Mistake Bounds when few Input Variables are Relevant. COLT Jyrki Kivinen, Manfred K. Warmuth
1995	—	`conf`	Tight worst-case loss bounds for predicting with expert advice. EuroCOLT David Haussler, Jyrki Kivinen, Manfred K. Warmuth
1995	A*	`conf`	Tracking the Best Disjunction. FOCS Peter Auer, Manfred K. Warmuth
1995	A*	`conf`	Tracking the Best Expert. ICML Mark Herbster, Manfred K. Warmuth
1995	—	`conf`	Worst-case Loss Bounds for Single Neurons. NIPS David P. Helmbold, Jyrki Kivinen, Manfred K. Warmuth
1994	J	`jnl`	Bounds on approximate steepest descent for likelihood maximization in exponential families. IEEE Trans. Inf. Theory Nicolò Cesa-Bianchi, Anders Krogh, Manfred K. Warmuth
1994	J	`jnl`	Composite Geometric Concepts and Polynomial Predictability Inf. Comput. Philip M. Long, Manfred K. Warmuth
1994	A*	`conf`	On the Worst-Case Analysis of Temporal-Difference Learning Algorithms. ICML Robert E. Schapire, Manfred K. Warmuth
1994	J	`jnl`	Predicting \0,1\-Functions on Randomly Drawn Points Inf. Comput. David Haussler, Nick Littlestone, Manfred K. Warmuth
1994	A*	`ed.`	Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, COLT 1994, New Brunswick, NJ, USA, July 12-15, 1994. COLT Manfred K. Warmuth
1994	J	`jnl`	The Distributed Bit Complexity of the Ring: From the Anonymous to the Non-anonymous Case Inf. Comput. Hans L. Bodlaender, Shlomo Moran, Manfred K. Warmuth
1994	J	`jnl`	The Weighted Majority Algorithm Inf. Comput. Nick Littlestone, Manfred K. Warmuth
1993	J	`jnl`	Gap Theorems for Distributed Computation. SIAM J. Comput. Shlomo Moran, Manfred K. Warmuth
1993	A*	`conf`	How to use expert advice. STOC Nicolò Cesa-Bianchi, Yoav Freund, David P. Helmbold, David Haussler, Robert E. Schapire, Manfred K. Warmuth
1993	A*	`conf`	Learning Binary Relations Using Weighted Majority Voting. COLT Sally A. Goldman, Manfred K. Warmuth
1993	—	`conf`	On-line prediction and conversion strategies. EuroCOLT Nicolò Cesa-Bianchi, Yoav Freund, David P. Helmbold, Manfred K. Warmuth
1993	J	`jnl`	The Minimum Consistent DFA Problem Cannot be Approximated within any Polynomial. J. ACM Leonard Pitt, Manfred K. Warmuth
1993	—	`conf`	Using experts for predicting continuous outcomes. EuroCOLT Jyrki Kivinen, Manfred K. Warmuth
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	J	`jnl`	Learning Integer Lattices. SIAM J. Comput. David P. Helmbold, Robert Sloan, Manfred K. Warmuth
1992	J	`jnl`	On the Computational Complexity of Approximating Distributions by Probabilistic Automata. Mach. Learn. Naoki Abe, Manfred K. Warmuth
1992	A*	`conf`	Some Weak Learning Results. COLT David P. Helmbold, Manfred K. Warmuth
1991	J	`jnl`	Equivalence of Models for Polynomial Learnability Inf. Comput. David Haussler, Michael J. Kearns, Nick Littlestone, Manfred K. Warmuth
1991	A*	`conf`	On-Line Learning of Linear Functions STOC Nick Littlestone, Philip M. Long, Manfred K. Warmuth
1991	A*	`conf`	Polynomial Learnability of Probabilistic Concepts with Respect to the Kullback-Leibler Divergence. COLT Naoki Abe, Manfred K. Warmuth, Jun'ichi Takeuchi
1991	A*	`ed.`	Proceedings of the Fourth Annual Workshop on Computational Learning Theory, COLT 1991, Santa Cruz, California, USA, August 5-7, 1991 COLT Manfred K. Warmuth, Leslie G. Valiant
1990	A*	`conf`	Composite Geometric Concepts and Polynomial Predictability. COLT Philip M. Long, Manfred K. Warmuth
1990	A*	`conf`	Learning Integer Lattices. COLT David P. Helmbold, Robert Sloan, Manfred K. Warmuth
1990	J	`jnl`	Learning Nested Differences of Intersection-Closed Concept Classes. Mach. Learn. David P. Helmbold, Robert Sloan, Manfred K. Warmuth
1990	J	`jnl`	NxN Puzzle and Related Relocation Problem. J. Symb. Comput. Daniel Ratner, Manfred K. Warmuth
1990	A*	`conf`	On the Computational Complexity of Approximating Distributions by Probabilistic Automata. COLT Naoki Abe, Manfred K. Warmuth
1990	J	`jnl`	Prediction-Preserving Reducibility. J. Comput. Syst. Sci. Leonard Pitt, Manfred K. Warmuth
1989	J	`jnl`	A Fast Algorithm for Multiprocessor Scheduling of Unit-Length Jobs. SIAM J. Comput. Barbara B. Simons, Manfred K. Warmuth
1989	J	`jnl`	Learnability and the Vapnik-Chervonenkis dimension. J. ACM Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, Manfred K. Warmuth
1989	A*	`conf`	Learning Nested Differences of Intersection-Closed Concept Classes. COLT David P. Helmbold, Robert Sloan, Manfred K. Warmuth
1989	J	`jnl`	Parallel Approximation Algorithms for Bin Packing Inf. Comput. Richard J. Anderson, Ernst W. Mayr, Manfred K. Warmuth
1989	A*	`ed.`	Proceedings of the Second Annual Workshop on Computational Learning Theory, COLT 1989, Santa Cruz, CA, USA, July 31 - August 2, 1989. COLT Ronald L. Rivest, David Haussler, Manfred K. Warmuth
1989	J	`jnl`	Scattered Versus Context-Sensitive Rewriting. Acta Informatica Jakob Gonczarowski, Manfred K. Warmuth
1989	B	`conf`	The Distributed Bit Complexity of the Ring: From the Anonymous to the Non-anonymous Case. FCT Hans L. Bodlaender, Shlomo Moran, Manfred K. Warmuth
1989	A*	`conf`	The Minimum Consistent DFA Problem Cannot Be Approximated within any Polynomial STOC Leonard Pitt, Manfred K. Warmuth
1989	—	`conf`	The Minimum Consistent DFA Problem Cannot be Approximated within any Polynomial (abstract). SCT Leonard Pitt, Manfred K. Warmuth
1989	A*	`conf`	The Weighted Majority Algorithm FOCS Nick Littlestone, Manfred K. Warmuth
1989	—	`conf`	Towards Representation Independence in PAC Learning. AII Manfred K. Warmuth
1988	J	`jnl`	Computing on an anonymous ring. J. ACM Hagit Attiya, Marc Snir, Manfred K. Warmuth
1988	A*	`conf`	Equivalence of Models for Polynomial Learnability. COLT David Haussler, Michael J. Kearns, Nick Littlestone, Manfred K. Warmuth
1988	A*	`conf`	Predicting {0, 1}-Functions on Randomly Drawn Points. COLT David Haussler, Nick Littlestone, Manfred K. Warmuth
1988	A*	`conf`	Predicting {0,1}-Functions on Randomly Drawn Points (Extended Abstract) FOCS David Haussler, Nick Littlestone, Manfred K. Warmuth
1988	—	`conf`	Reductions among prediction problems: on the difficulty of predicting automata. SCT Leonard Pitt, Manfred K. Warmuth
1987	J	`jnl`	Occam's Razor. Inf. Process. Lett. Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, Manfred K. Warmuth
1986	A*	`conf`	Classifying Learnable Geometric Concepts with the Vapnik-Chervonenkis Dimension (Extended Abstract) STOC Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, Manfred K. Warmuth
1986	A*	`conf`	Finding a Shortest Solution for the N × N Extension of the 15-PUZZLE Is Intractable. AAAI Daniel Ratner, Manfred K. Warmuth
1986	A*	`conf`	Gap Theorems for Distributed Computation. PODC Shlomo Moran, Manfred K. Warmuth
1986	J	`jnl`	Manipulating Derivation Forests by Scheduling Techniques. Theor. Comput. Sci. Jakob Gonczarowski, Manfred K. Warmuth
1986	—	`conf`	Membership for Growing Context Sensitive Grammars is Polynomial. CAAP Elias Dahlhaus, Manfred K. Warmuth
1986	J	`jnl`	Membership for Growing Context-Sensitive Grammars is Polynomial. J. Comput. Syst. Sci. Elias Dahlhaus, Manfred K. Warmuth
1986	J	`jnl`	The Parallel Complexity of Scheduling with Precedence Constraints. J. Parallel Distributed Comput. Danny Dolev, Eli Upfal, Manfred K. Warmuth
1985	J	`jnl`	Applications of Scheduling Theory to Formal Language Theory. Theor. Comput. Sci. Jakob Gonczarowski, Manfred K. Warmuth
1985	A*	`conf`	Computing on an Anonymous Ring. PODC Chagit Attiya, Marc Snir, Manfred K. Warmuth
1985	J	`jnl`	Scheduling Flat Graphs. SIAM J. Comput. Danny Dolev, Manfred K. Warmuth
1984	J	`jnl`	On the Complexity of Iterated Shuffle. J. Comput. Syst. Sci. Manfred K. Warmuth, David Haussler
1984	J	`jnl`	Scheduling Precedence Graphs of Bounded Height. J. Algorithms Danny Dolev, Manfred K. Warmuth