← Authors

Manfred K. Warmuth

42 papers · 2001–2025 · 8 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (24) 🌍 Conference Polyglot (8) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (15) πŸ—ΊοΈ Taxonomy Completionist (19) 🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer 🌟 Keyword Trendsetter Combo (3) πŸ”¬ Deep Specialist (16) πŸ† Keyword Champion (2) 🌱 Topic Pioneer 🀝 Dynamic Duo (12) πŸ”₯ Unstoppable (21) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer ⚑ Prolific Year (5) πŸ’Ž Century Club (42) πŸ—ƒοΈ Keyword Collector (60)

Conferences

NIPS (12) JMLR (11) COLT (9) AISTATS (3) ALT (3) AAAI (2) ICML (1) UAI (1)

Top co-authors

Ehsan Amid (12) Wouter M. Koolen (5) Michal Derezinski (4) Dima Kuzmin (3) Wojciech Kotlowski (3) Wojciech KotΕ‚owski (3) MichaΕ‚ DereziΕ„ski (3) Richard Nock (3) Gunnar RΓ€tsch (3) Daniel Hsu (2)

Keywords

online learning (17) regret bound (9) linear regression (7) least square (5) gradient descent (5) unbiased estimator (5) volume sampling (4) online algorithm (3) kernel methods (3) principal component analysis (3) dimensionality reduction (3) multiplicative update (3) determinantal point process (2) ensemble learning (2) expert advice (2) sparse linear regression (2) posterior mixing (2) bregman divergence (2) relative entropy (2) matrix factorization (2)

Papers

How rotation invariant algorithms are fooled by noise on sparse targets ALT 2025
Optimal Transport with Tempered Exponential Measures AAAI 2024
A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks ALT 2024
Hyperbolic Embeddings of Supervised Models NIPS 2024
Clustering above Exponential Families with Tempered Exponential Measures AISTATS 2023
Open Problem: Learning sparse linear concepts by priming the features COLT 2023
Unbiased estimators for random design regression JMLR 2022
A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer ALT 2021
An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint AAAI 2020
Reparameterizing Mirror Descent as Gradient Descent NIPS 2020
Winnowing with Gradient Descent COLT 2020
Divergence-Based Motivation for Online EM and Combining Hidden Variable Models UAI 2020
Robust Bi-Tempered Logistic Loss Based on Bregman Divergences NIPS 2019
Correcting the bias in least squares regression with volume-rescaled sampling AISTATS 2019
Two-temperature logistic regression based on the Tsallis divergence AISTATS 2019
Adaptive Scale-Invariant Online Algorithms for Learning Linear Models ICML 2019
Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression COLT 2019
Reverse Iterative Volume Sampling for Linear Regression JMLR 2018
Leveraged volume sampling for linear regression NIPS 2018
Online Dynamic Programming NIPS 2017
Unbiased estimates for linear regression via volume sampling NIPS 2017
Online PCA with Optimal Regret JMLR 2016
Minimax Fixed-Design Linear Regression COLT 2015
Open Problem: Online Sabotaged Shortest Path COLT 2015
The limits of squared Euclidean distance regularization NIPS 2014
Open Problem: Shifting Experts on Easy Data COLT 2014
Follow the Leader with Dropout Perturbations COLT 2014
Open Problem: Lower bounds for Boosting with Hadamard Matrices COLT 2013
Putting Bayes to sleep NIPS 2012
Learning Eigenvectors for Free NIPS 2011
Minimax Algorithm for Learning Rotations COLT 2011
Repeated Games against Budgeted Adversaries NIPS 2010
Learning Permutations with Exponential Weights JMLR 2009
Randomized Online PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension JMLR 2008
Boosting Algorithms for Maximizing the Soft Margin NIPS 2007
Unlabeled Compression Schemes for Maximum Classes JMLR 2007
Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension NIPS 2006
Efficient Margin Maximizing with Boosting JMLR 2005
Matrix Exponentiated Gradient Updates for On-line Learning and Bregman Projection JMLR 2005
Path Kernels and Multiplicative Updates JMLR 2003
Tracking a Small Set of Experts by Mixing Past Posteriors JMLR 2002
Tracking the Best Linear Predictor JMLR 2001