Welcome
Home
Courses
Recent news
Selected Talks
Research Papers
All Papers 
(…)
Minimally Supervised Learning
(Active Leaning, Transfer Learning, ..)
Unsupervised Learning
(Clustering, Causality, Geometric Graphs, ..)
Supervised Learning
(Manifold, Sparsity, Tradeoffs, ..)
Miscellaneous
Software Code

All Papers

Working papers and preprints:

  • Steve Hanneke, Samory Kpotufe. A More Unified Theory of Transfer Learning.
    [ arXiv ]

  • Mohammadreza M. Kalan, Samory Kpotufe. Distribution-Free Rates in Neyman-Pearson Classification.
    [ arXiv ]

  • Dimitri Meunier, Zhu Li, Arthur Gretton, Samory Kpotufe. Nonlinear Meta-Learning Can Guarantee Faster Rates.
    [ arXiv ]

  • Gan Yuan, Mingyue Xu, Samory Kpotufe, Daniel Hsu. Efficient Estimation of the Central Mean Subspace via Smooth Gradient Outer Products.
    [ arXiv ]

Published papers:

  • Mohammadreza M. Kalan, Samory Kpotufe. Tight Rates in Supervised Outlier Transfer Learning.
    ICLR 2024. [ arXiv ]

  • Gan Yuan, Yunfan Zhao. Samory Kpotufe. Regimes of no gain in multi-class active learning..
    Journal of Machine Learning Research (JMLR) 2024. [ PDF ]

  • Nicholas Galbraith, Samory Kpotufe. Classification Tree Pruning Under Covariate Shift.
    IEEE Transactions on Information Theory 2024. [ arXiv ]

  • Joe Suk, Samory Kpotufe. Tracking Most Significant Switches in Nonparametric Contextual Bandits.
    Neural Information Processing Systems (NeurIPS) 2023. [ arXiv ]

  • Steve Hanneke, Samory Kpotufe, Yasaman Mahdaviyeh. Limits of Model Selection Under Transfer Learning.
    Conference on Learning Theory (COLT) 2023. [ arXiv ]

  • Kun Yang, Samory Kpotufe, Nick Feamster. An efficient one-class SVM for anomaly detection in the Internet of Things.
    Transactions on Machine Learning Research (TMLR) 2022. [ arXiv ]

  • Joe Suk, Samory Kpotufe. Tracking Most Severe Arm Changes in Bandits.
    Conference on Learning Theory (COLT) 2022. [ arXiv ]

  • Samory Kpotufe, Gan Yuan, Yunfan Zhao. Nuances in Margin Conditions Determine Gains in Active Learning.
    Artificial Intelligence and Statistics (AISTATS) 2022. [ arXiv ]

  • Steve Hanneke, Samory Kpotufe. A No-Free-Lunch Theorem For Multitask Learning.
    Annals of Statistics 2022. [ arXiv ]

  • Samory Kpotufe, Guillaume Martinet. Marginal Singularity, and the Benefits of Labels in Covariate-Shift.
    Annals of Statistics 2021. [ arXiv ]

  • Joe Suk, Samory Kpotufe. Self-Tuning Bandits over Unknown Covariate-Shifts.
    Algorithmic Learning Theory (ALT) 2020. [ arXiv ]

  • Samory Kpotufe, Bharath Sriperumbudur. Gaussian Sketching yields a JL lemma in RKHS.
    Artificial Intelligence and Statistics (AISTATS) 2020. [ earlier arXiv version ]

  • Sanjoy Dasgupta, Samory Kpotufe. Nearest Neighbor Classification and Search.
    Invited Chapter in Beyond Worst-Case Analysis, Cambridge University Press, 2019, edited by Tim Roughgarden. [ pdf ]

  • Steve Hanneke, Samory Kpotufe. On the Value of Target Data in Transfer Learning.
    Neural Information Processing Systems (NeurIPS) 2019. [ pdf ]

  • Tin Nguyen, Samory Kpotufe. PAC-Bayes Tree: weighted subtrees with guarantees.
    Neural Information Processing Systems (NeurIPS) 2018. [ pdf ]

  • Heinrich Jiang, Jennifer Jang, Samory Kpotufe. Quickshift++: Provably good initializations for sample-based mean Shift.
    International Conference on Machine Learning (ICML) 2018. [ arXiv ]

  • Samory Kpotufe, Guillaume Martinet. Marginal Singularity, and the Benefits of Labels in Covariate-Shift.
    Accepted abstract at Conference on Learning Theory (COLT) 2018. [ arXiv ]

  • Andrea Locatelli, Alexandra, Carpentier, Samory Kpotufe. An Adaptive Strategy for Active Learning with Smooth Decision Boundary.
    Algorithmic Learning Theory (ALT) 2018. [ arXiv ]

  • Lirong Xue, Samory Kpotufe. Achieving the time of 1-NN, but the accuracy of k-NN.
    Artificial Intelligence and Statistics (AISTATS) 2018. [ arXiv ]

  • Samory Kpotufe, Nakul Verma. Time-Accuracy Tradeoffs in Kernel Prediction: Controlling Prediction Quality.
    Journal of Machine Learning Research (JMLR) 2017. [ pdf ]

  • Andrea Locatelli, Alexandra, Carpentier, Samory Kpotufe. Adaptivity to Noise Parameters in Nonparametric Active Learning.
    Conference on Learning Theory (COLT) 2017. [ pdf ]

  • Heinrich Jiang, Samory Kpotufe. Modal-set estimation with an application to clustering.
    Artificial Intelligence and Statistics (AISTATS) 2017. Selected for Plenary Presentation. [ pdf ]

  • Samory Kpotufe. Lipschitz Density-Ratios, Structured Data, and Data-driven Tuning.
    Artificial Intelligence and Statistics (AISTATS) 2017. [ pdf ]

  • Samory Kpotufe, Abdeslam Boularias, Thomas Schultz, Kyoungok Kim. Gradients Weights improve Regression and Classification.
    Journal Of Machine Learning Research (JMLR) 2016. [ pdf ]

  • Samory Kpotufe, Ruth Urner, Shai Ben-David. Hierarchical label queries with data-dependent partitions.
    Conference on Learning Theory (COLT) 2015. [ pdf ]

  • Sanjoy Dasgupta, Samory Kpotufe. Optimal rates for k-NN density and mode estimation.
    Neural Information Processing Systems (NeurIPS) 2014. [ pdf | slides (CIRM, Luminy)]

  • Kamalika Chaudhuri, Sanjoy Dasgupta, Samory Kpotufe, Ulrike von Luxburg. Consistent procedures for cluster-tree estimation and pruning.
    IEEE Transactions on Information Theory, 60(12):7900-7912, 2014. [ pdf ]

  • Shubhendu Trivedi, Jialei Wang, Samory Kpotufe, Gregory Shakhnarovich. A Consistent Estimator of the Expected Gradient Outerproduct.
    Uncertainty in Artificial Intelligence (UAI) 2014. [ pdf ]

  • Samory Kpotufe, Eleni Sgouritsa, Dominik Janzing, Bernhard Schoelkopf. Consistency of Causal Inference under the Additive Noise Model.
    International Conference on Machine Learning (ICML) 2014. [ pdf ]

  • Samory Kpotufe, Vikas K. Garg. Adaptivity to Local Smoothness and Dimension in Kernel Regression.
    Neural Information Processing Sytems (NeurIPS) 2013. [ pdf ]

  • Samory Kpotufe, Francesco Orabona. Regression-tree Tuning in a Streaming Setting.
    Neural Information Processing Sytems (NeurIPS) 2013. Selected for Spotlight (one of 52/1420 submissions). [ pdf ]

  • Samory Kpotufe, Abdeslam Boularias. Gradient weights help nonparametric regressors.
    Neural Information Processing Sytems (NeurIPS) 2012. Selected for Plenary Presentation (one of 20/1467 submissions). [ pdf ]

  • Samory Kpotufe. k-NN Regression adapts to local intrinsic dimension.
    Neural Information Processing Sytems (NeurIPS) 2011. Selected for Plenary Presentation (one of 20/1400 submissions). [ pdf ]

  • Samory Kpotufe, Ulrike von Luxburg. Pruning nearest neighbor cluster trees.
    International Conference on Machine Learning (ICML) 2011. [ pdf | slides ]

  • Samory Kpotufe, Sanjoy Dasgupta. A tree-based regressor that adapts to intrinsic dimension.
    Invited to Special Issue of the Journal of Computer and Systems Sciences (JCSS) 2011. [ pdf ]

  • Samory Kpotufe. The curse of dimension in nonparametric regression.
    UCSD, Phd Dissertation 2010. [ pdf ]

  • Eric Flynn, Samory Kpotufe, et al. SHMTools: a new embeddable software package for SHM applications.
    SPIE 2010.

  • Samory Kpotufe. Escaping the curse of dimensionality with a tree-based regressor.
    Conference on Learning Theory (COLT) 2009. Mark Fulk Best Student Paper. [ pdf | slides ]

  • Nakul Verma, Samory Kpotufe, Sanjoy Dasgupta. Which spatial partition trees are adaptive to intrinsic dimension?
    Uncertainty in Artificial Intelligence (UAI) 2009. [ pdf | poster ]

  • Samory Kpotufe. Fast, smooth and adaptive regression in metric spaces.
    Neural Information Processing Sytems (NeurIPS) 2009. [ pdf ]