Last ten or so pubs of Manfred K. Warmuth

Last ten or so pubs of Manfred K. Warmuth



  • Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression arXiv

  • Adaptive scale-invariant online algorithms for learning linear models arXiv

  • Divergence-Based Motivation for Online EM and Combining Hidden Variable Models arXiv

  • Unlabeled sample compression schemes and corner peelings for ample and maximum classes arXiv

  • Two-temperature logistic regression based on the Tsallis divergence, to appear in AISTATS19, pdf

  • Correcting the bias in least squares regression with volume-rescaled sampling, to appear in AISTATS19, arXiv

  • Online Non-Additive Path Learning under Full and Partial Information, to appear in ALT19, arXiv

  • Leveraged volume sampling for linear regression. To appear in NIPS18 NIPS18 paper

  • Reverse iterative volume sampling for linear regression
    Journal paper about the following 2 conference papers and more [JMLR paper]
    Long talk about volume sampling [talk]

  • Subsampling for Ridge Regression via Regularized Volume Sampling [AISTATS18 paper] [talk]

  • Unbiased estimates for linear regression via volume sampling [NIPS17 paper] [poster]

  • Online dynamic programming [NIPS17 paper]

  • Labeled compression schemes for extremal classes [ALT16 paper]

  • Minimax Fixed-Design Linear Regression [COLT15 paper]

  • Online Learning Algorithms for Path Experts with Non-Additive Losses [COLT15 paper]

  • Online Sabotaged Shortest Path [COLT15 open problem]

  • The blessing and the curse of the multiplicative updates [video] [slides] [book chapter]