Publications

You can also find my articles on my Google Scholar profile.

Decision tree learning

• J. M. Klusowski, “Universal consistency of decision trees in high dimensions,” Submitted, 2021. [updated] [preprint]
• J. M. Klusowski and P. M. Tian, “Nonparametric variable screening with optimal decision stumps,” AISTATS, 2021. [proceedings]
• J. M. Klusowski, “Sparse learning with CART,” [preprint]
  • NeurIPS, 2020. [proceedings] [poster]
  • Longer version revise and resubmit to IEEE Transactions on Information Theory, 2020.
• J. M. Klusowski, “Analyzing CART,” Technical report, 2019. [preprint] (Some content in this paper appeared in “Sparse learning with CART.”)
• J. M. Klusowski, “Sharp analysis of a simple model for random forests,” AISTATS, 2021. [proceedings]

Neural networks

• J. M. Klusowski, “Total path variation for deep nets with general activation functions,” Technical report, 2019. [preprint]
• A. R. Barron and J. M. Klusowski, “Approximation and estimation for high-dimensional deep learning networks,” Submitted, 2018. [preprint]
• J. M. Klusowski and A. R. Barron, “Approximation by combinations of ReLU and squared ReLU ridge functions with $\ell^1$ and $\ell^0$ controls,” IEEE Transactions on Information Theory, 2018. [preprint] [journal]
• J. M. Klusowski and A. R. Barron, “Risk bounds for high-dimensional ridge function combinations including neural networks,” Technical report, 2018. [preprint]
• J. M. Klusowski and A. R. Barron, “Minimax lower bounds for ridge combinations including neural nets,” Proceedings IEEE International Symposium on Information Theory, Aachen, Germany, 2017. [preprint] [proceedings]

High-dimensional linear models

• R. Theisen, J. M. Klusowski, M. W. Mahoney, “Good classifiers are abundant in the interpolating regime,” AISTATS, 2021. [preprint] [proceedings]
• Z. Bu, J. M. Klusowski, C. Rush, W. J. Su, “Algorithmic analysis and statistical estimation of SLOPE via approximate message passing,”
  • NeurIPS, 2019. [proceedings] [poster]
  • Longer version in IEEE Transactions on Information Theory, 2020. [preprint] [journal]
• Z. Bu, J. M. Klusowski, C. Rush, W. J. Su, “Characterizing the SLOPE Trade-off: A Variational Perspective and the Donoho–Tanner Limit,” Submitted, 2021. [preprint]

Mixture models

• J. M. Klusowski, D. Yang, and W. D. Brinda, “Estimating the coefficients of a mixture of two linear regressions by expectation maximization,” IEEE Transactions on Information Theory, 2019. [preprint] [journal]
• J. M. Klusowski and W. D. Brinda, “Statistical guarantees for estimating the centers of a two-component Gaussian mixture by EM,” Technical report, 2016. [preprint]

Network analysis

• J. M. Klusowski and Y. Wu, “Estimating the number of connected components in a graph via subgraph sampling,” Bernoulli, 2020. [preprint] [journal]
• J. M. Klusowski and Y. Wu, “Counting motifs with graph sampling,” Conference on Learning Theory (COLT), 2018. [preprint] [proceedings] [poster]

Shaped constrained estimation

• V. E. Brunel, J. M. Klusowski, and D. Yang, “Estimation of convex supports from noisy measurements,” Bernoulli, 2021. [preprint]

Miscellaneous

• W. D. Brinda, J. M. Klusowski, and D. Yang, “Hölder’s identity,” Statistics and Probability Letters, 2019. [journal]
• W. D. Brinda and J. M. Klusowski, “Finite-sample risk bounds for maximum likelihood estimation with arbitrary penalties,” IEEE Transactions on Information Theory, 2018. [preprint] [journal]