| 2025 | ALT | How rotation invariant algorithms are fooled by noise on sparse targets. | Manfred K. Warmuth, Wojciech Kotlowski, Matt Jones, Ehsan Amid |
| 2024 | AAAI | Optimal Transport with Tempered Exponential Measures. | Ehsan Amid, Frank Nielsen, Richard Nock, Manfred K. Warmuth |
| 2024 | ALT | A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks. | Jacob D. Abernethy, Alekh Agarwal, Teodor Vanislavov Marinov, Manfred K. Warmuth |
| 2023 | AISTATS | Clustering above Exponential Families with Tempered Exponential Measures. | Ehsan Amid, Richard Nock, Manfred K. Warmuth |
| 2023 | COLT | Open Problem: Learning sparse linear concepts by priming the features. | Manfred K. Warmuth, Ehsan Amid |
| 2022 | AISTATS | LocoProp: Enhancing BackProp via Local Loss Optimization. | Ehsan Amid, Rohan Anil, Manfred K. Warmuth |
| 2021 | ALT | A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer. | Manfred K. Warmuth, Wojciech Kotlowski, Ehsan Amid |
| 2020 | AAAI | An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint. | Ehsan Amid, Manfred K. Warmuth |
| 2020 | COLT | Winnowing with Gradient Descent. | Ehsan Amid, Manfred K. Warmuth |
| 2020 | ICIP | Rank-Smoothed Pairwise Learning In Perceptual Quality Assessment. | Hossein Talebi, Ehsan Amid, Peyman Milanfar, Manfred K. Warmuth |
| 2020 | UAI | Divergence-Based Motivation for Online EM and Combining Hidden Variable Models. | Ehsan Amid, Manfred K. Warmuth |
| 2019 | AISTATS | Two-temperature logistic regression based on the Tsallis divergence. | Ehsan Amid, Manfred K. Warmuth, Sriram Srinivasan |
| 2019 | AISTATS | Correcting the bias in least squares regression with volume-rescaled sampling. | Michal Derezinski, Manfred K. Warmuth, Daniel Hsu |
| 2019 | ALT | Online Non-Additive Path Learning under Full and Partial Information. | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Holakou Rahmanian, Manfred K. Warmuth |
| 2019 | COLT | Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. | Michal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth |
| 2019 | ICALP | Unlabeled Sample Compression Schemes and Corner Peelings for Ample and Maximum Classes. | Jrmie Chalopin, Victor Chepoi, Shay Moran, Manfred K. Warmuth |
| 2019 | ICML | Adaptive Scale-Invariant Online Algorithms for Learning Linear Models. | Michal Kempka, Wojciech Kotlowski, Manfred K. Warmuth |
| 2018 | AISTATS | Subsampling for Ridge Regression via Regularized Volume Sampling. | Michal Derezinski, Manfred K. Warmuth |
| 2016 | ALT | Labeled Compression Schemes for Extremal Classes. | Shay Moran, Manfred K. Warmuth |
| 2016 | LATA | Noise Free Multi-armed Bandit Game. | Atsuyoshi Nakamura, David P. Helmbold, Manfred K. Warmuth |
| 2015 | COLT | Minimax Fixed-Design Linear Regression. | Peter L. Bartlett, Wouter M. Koolen, Alan Malek, Eiji Takimoto, Manfred K. Warmuth |
| 2015 | COLT | On-Line Learning Algorithms for Path Experts with Non-Additive Losses. | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Manfred K. Warmuth |
| 2015 | COLT | Open Problem: Online Sabotaged Shortest Path. | Wouter M. Koolen, Manfred K. Warmuth, Dmitry Adamskiy |
| 2014 | COLT | Open Problem: Shifting Experts on Easy Data. | Manfred K. Warmuth, Wouter M. Koolen |
| 2013 | ALT | Online PCA with Optimal Regrets. | Jiazhong Nie, Wojciech Kotlowski, Manfred K. Warmuth |
| 2013 | COLT | Learning a set of directions. | Wouter M. Koolen, Jiazhong Nie, Manfred K. Warmuth |
| 2013 | COLT | Open Problem: Lower bounds for Boosting with Hadamard Matrices. | Jiazhong Nie, Manfred K. Warmuth, S. V. N. Vishwanathan, Xinhua Zhang |
| 2012 | ALT | Kernelization of Matrix Updates, When and How? | Manfred K. Warmuth, Wojciech Kotlowski, Shuisheng Zhou |
| 2011 | ALT | Combining Initial Segments of Lists. | Manfred K. Warmuth, Wouter M. Koolen, David P. Helmbold |
| 2010 | ALT | The Blessing and the Curse of the Multiplicative Updates. | Manfred K. Warmuth |
| 2010 | COLT | Learning Rotations with Little Regret. | Elad Hazan, Satyen Kale, Manfred K. Warmuth |
| 2010 | COLT | On-line Variance Minimization in O(n2) per Trial? | Elad Hazan, Satyen Kale, Manfred K. Warmuth |
| 2010 | COLT | Hedging Structured Concepts. | Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivinen |
| 2010 | DIS | The Blessing and the Curse of the Multiplicative Updates. | Manfred K. Warmuth |
| 2010 | ICNC | New combination coefficients for AdaBoost algorithms. | Shuisheng Zhou, Manfred K. Warmuth, Yinli Dong, Feng Ye |
| 2009 | COLT | Minimax Games with Bandits. | Jacob D. Abernethy, Manfred K. Warmuth |
| 2009 | ICML | Tutorial summary: Survey of boosting from an optimization perspective. | Manfred K. Warmuth, S. V. N. Vishwanathan |
| 2008 | ALT | Entropy Regularized LPBoost. | Manfred K. Warmuth, Karen A. Glocer, S. V. N. Vishwanathan |
| 2008 | COLT | When Random Play is Optimal Against an Adversary. | Jacob D. Abernethy, Manfred K. Warmuth, Joel Yellin |
| 2008 | COLT | Learning Rotations. | Adam M. Smith, Manfred K. Warmuth |
| 2007 | COLT | Learning Permutations with Exponential Weights. | David P. Helmbold, Manfred K. Warmuth |
| 2007 | COLT | When Is There a Free Matrix Lunch? | Manfred K. Warmuth |
| 2007 | ICML | Online kernel PCA with entropic matrix updates. | Dima Kuzmin, Manfred K. Warmuth |
| 2007 | ICML | Winnowing subspaces. | Manfred K. Warmuth |
| 2006 | COLT | Continuous Experts and the Binning Algorithm. | Jacob D. Abernethy, John Langford, Manfred K. Warmuth |
| 2006 | COLT | Can Entropic Regularization Be Replaced by Squared Euclidean Distance Plus Additional Linear Constraints. | Manfred K. Warmuth |
| 2006 | COLT | Online Variance Minimization. | Manfred K. Warmuth, Dima Kuzmin |
| 2006 | ICML | Totally corrective boosting algorithms that maximize the margin. | Manfred K. Warmuth, Jun Liao, Gunnar Rtsch |
| 2006 | UAI | A Bayesian Probability Calculus for Density Matrices. | Manfred K. Warmuth, Dima Kuzmin |
| 2005 | COLT | Unlabeled Compression Schemes for Maximum Classes, . | Dima Kuzmin, Manfred K. Warmuth |
| 2005 | COLT | Optimum Follow the Leader Algorithm. | Dima Kuzmin, Manfred K. Warmuth |
| 2005 | COLT | Leaving the Span. | Manfred K. Warmuth, S. V. N. Vishwanathan |
| 2004 | COLT | The Optimal PAC Algorithm. | Manfred K. Warmuth |
| 2003 | COLT | Compressing to VC Dimension Many Points. | Manfred K. Warmuth |
| 2003 | Interspeech | Inline updates for HMMs. | Ashutosh Garg, Manfred K. Warmuth |
| 2003 | Interspeech | Classification with free energy at raised temperatures. | Rita Singh, Manfred K. Warmuth, Bhiksha Raj, Paul Lamere |
| 2002 | COLT | Maximizing the Margin with Boosting. | Gunnar Rtsch, Manfred K. Warmuth |
| 2002 | COLT | Path Kernels and Multiplicative Updates. | Eiji Takimoto, Manfred K. Warmuth |
| 2001 | COLT | Tracking a Small Set of Experts by Mixing Past Posteriors. | Olivier Bousquet, Manfred K. Warmuth |
| 2000 | ALT | The Last-Step Minimax Algorithm. | Eiji Takimoto, Manfred K. Warmuth |
| 2000 | COLT | Relative Expected Instantaneous Loss Bounds. | Jrgen Forster, Manfred K. Warmuth |
| 2000 | COLT | Barrier Boosting. | Gunnar Rtsch, Manfred K. Warmuth, Sebastian Mika, Takashi Onoda, Steven Lemm, Klaus-Robert Mller |
| 2000 | COLT | The Minimax Strategy for Gaussian Density Estimation. pp. | Eiji Takimoto, Manfred K. Warmuth |
| 2000 | ICML | Relative Loss Bounds for Temporal-Difference Learning. | Jrgen Forster, Manfred K. Warmuth |
| 1999 | ALT | Predicting Nearly as well as the best Pruning of a Planar Decision Graph. | Eiji Takimoto, Manfred K. Warmuth |
| 1999 | COLT | Boosting as Entropy Projection. | Jyrki Kivinen, Manfred K. Warmuth |
| 1999 | UAI | Relative Loss Bounds for On-line Density Estirnation with the Exponential Family of Distributions. | Katy S. Azoury, Manfred K. Warmuth |
| 1998 | COLT | Tracking the Best Regressor. | Mark Herbster, Manfred K. Warmuth |
| 1997 | STOC | Using and Combining Predictors That Specialize. | Yoav Freund, Robert E. Schapire, Yoram Singer, Manfred K. Warmuth |
| 1996 | COLT | Learning of Depth Two Neural Networks with Constant Fan-In at the Hidden Nodes (Extended Abstract). | Peter Auer, Stephen Kwek, Wolfgang Maass, Manfred K. Warmuth |
| 1996 | ICML | On-Line Portfolio Selection Using Multiplicative Updates. | David P. Helmbold, Robert E. Schapire, Yoram Singer, Manfred K. Warmuth |
| 1995 | COLT | A Comparison of New and Old Algorithms for a Mixture Estimation Problem. | David P. Helmbold, Yoram Singer, Robert E. Schapire, Manfred K. Warmuth |
| 1995 | COLT | The Perceptron Algorithm vs. Winnow: Linear vs. Logarithmic Mistake Bounds when few Input Variables are Relevant. | Jyrki Kivinen, Manfred K. Warmuth |
| 1995 | FOCS | Tracking the Best Disjunction. | Peter Auer, Manfred K. Warmuth |
| 1995 | ICML | Tracking the Best Expert. | Mark Herbster, Manfred K. Warmuth |
| 1995 | ICML | Efficient Learning with Virtual Threshold Gates. | Wolfgang Maass, Manfred K. Warmuth |
| 1995 | STOC | Additive versus exponentiated gradient updates for linear prediction. | Jyrki Kivinen, Manfred K. Warmuth |
| 1994 | ICML | On the Worst-Case Analysis of Temporal-Difference Learning Algorithms. | Robert E. Schapire, Manfred K. Warmuth |
| 1993 | COLT | Worst-Case Quadratic Loss Bounds for a Generalization of the Widrow-Hoff Rule. | Nicol Cesa-Bianchi, Philip M. Long, Manfred K. Warmuth |
| 1993 | COLT | Learning Binary Relations Using Weighted Majority Voting. | Sally A. Goldman, Manfred K. Warmuth |
| 1993 | STOC | How to use expert advice. | Nicol Cesa-Bianchi, Yoav Freund, David P. Helmbold, David Haussler, Robert E. Schapire, Manfred K. Warmuth |
| 1992 | COLT | Some Weak Learning Results. | David P. Helmbold, Manfred K. Warmuth |
| 1991 | COLT | Polynomial Learnability of Probabilistic Concepts with Respect to the Kullback-Leibler Divergence. | Naoki Abe, Manfred K. Warmuth, Jun'ichi Takeuchi |
| 1991 | STOC | On-Line Learning of Linear Functions | Nick Littlestone, Philip M. Long, Manfred K. Warmuth |
| 1990 | COLT | On the Computational Complexity of Approximating Distributions by Probabilistic Automata. | Naoki Abe, Manfred K. Warmuth |
| 1990 | COLT | Learning Integer Lattices. | David P. Helmbold, Robert Sloan, Manfred K. Warmuth |
| 1990 | COLT | Composite Geometric Concepts and Polynomial Predictability. | Philip M. Long, Manfred K. Warmuth |
| 1989 | COLT | Learning Nested Differences of Intersection-Closed Concept Classes. | David P. Helmbold, Robert Sloan, Manfred K. Warmuth |
| 1989 | FCT | The Distributed Bit Complexity of the Ring: From the Anonymous to the Non-anonymous Case. | Hans L. Bodlaender, Shlomo Moran, Manfred K. Warmuth |
| 1989 | FOCS | The Weighted Majority Algorithm | Nick Littlestone, Manfred K. Warmuth |
| 1989 | STOC | The Minimum Consistent DFA Problem Cannot Be Approximated within any Polynomial | Leonard Pitt, Manfred K. Warmuth |
| 1988 | COLT | Equivalence of Models for Polynomial Learnability. | David Haussler, Michael J. Kearns, Nick Littlestone, Manfred K. Warmuth |
| 1988 | COLT | Predicting {0, 1}-Functions on Randomly Drawn Points. | David Haussler, Nick Littlestone, Manfred K. Warmuth |
| 1988 | FOCS | Predicting {0,1}-Functions on Randomly Drawn Points (Extended Abstract) | David Haussler, Nick Littlestone, Manfred K. Warmuth |
| 1986 | AAAI | Finding a Shortest Solution for the N × N Extension of the 15-PUZZLE Is Intractable. | Daniel Ratner, Manfred K. Warmuth |
| 1986 | PODC | Gap Theorems for Distributed Computation. | Shlomo Moran, Manfred K. Warmuth |
| 1986 | STOC | Classifying Learnable Geometric Concepts with the Vapnik-Chervonenkis Dimension (Extended Abstract) | Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, Manfred K. Warmuth |
| 1985 | PODC | Computing on an Anonymous Ring. | Chagit Attiya, Marc Snir, Manfred K. Warmuth |