Manuscripts

. Interpolating Classifiers Make Few Mistake. arXiv:2101.xxxxx, 2021.

Preprint PDF

. A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-L1-Norm Interpolated Classifiers. arXiv:2002.01586, 2020.

Preprint PDF

. Deep Learning for Individual Heterogeneity. arXiv:2010.14694, 2020.

Preprint

. Estimating Certain Integral Probability Metrics (IPMs) Is as Hard as Estimating under the IPMs. arXiv:1911.00730, 2019.

Preprint PDF

. How Well Generative Adversarial Networks Learn Distributions. arXiv:1811.03179, 2018.

Preprint PDF

Publications

More Publications

. Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks. Journal of the American Statistical Association (Theory and Methods), forthcoming, 2020.

Preprint PDF

. Deep Neural Networks for Estimation and Inference. Econometrica, 2020.

Preprint PDF Media

. On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels. Conference on Learning Theory (COLT), 2020.

Preprint PDF

. Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits. Journal of the American Statistical Association (Theory and Methods), 2020.

Preprint PDF

. Just Interpolate: Kernel ''Ridgeless'' Regression Can Generalize. Annals of Statistics, 2020.

Preprint PDF Supplement

. Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information. Journal of Machine Learning Research, 2020.

Preprint PDF

. Statistical Inference for the Population Landscape via Moment Adjusted Stochastic Gradients. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2019.

Preprint PDF

. Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

Preprint PDF

. Fisher-Rao Metric, Geometry, and Complexity of Neural Networks. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

Preprint PDF

. Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability. Conference on Learning Theory (COLT), 2018.

Preprint PDF

. Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP. International Conference on Machine Learning (ICML), 2017.

Preprint PDF

. Computational and Statistical Boundaries for Submatrix Localization in a Large Noisy Matrix. Annals of Statistics, 2017.

Preprint PDF

. On Detection and Structural Reconstruction of Small-World Random Networks. IEEE Transactions on Network Science and Engineering, 2017.

Preprint PDF

. Geometric Inference for General High-Dimensional Linear Inverse Problems. Annals of Statistics, 2016.

Preprint PDF

. Learning with Square Loss: Localization through Offset Rademacher Complexity. Conference on Learning Theory (COLT), 2015.

Preprint PDF

. Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions. Conference on Learning Theory (COLT), 2015.

Preprint PDF

. Law of Log Determinant of Sample Covariance Matrix and Optimal Estimation of Differential Entropy for High-Dimensional Gaussian Distributions. Journal of Multivariate Analysis, 2015.

Preprint PDF

Workshops & Talks

More Talks

NSF-Simons Collaboration, Mathematics of Deep Learning
Dec 16, 2020
Mathematics of Deep Learning Workshop
JSM 2020
Aug 5, 2020
Theoretical Advances in Deep Learning, IMS Invited Session
Slides
Google Research NYC
Jun 12, 2020
Learning Theory Seminar
Slides
Duke
Mar 25, 2020
TRIPODS Workshop on Theory and Modeling of Deep Learning
Slides
MIT
Jan 27, 2020
MIFODS Workshop on Learning with a Complex Structure
Harvard
Sep 16, 2019
Statistics Colloquium, Dept. of Statistics
Yale
Sep 11, 2019
Econometrics Seminar, Dept. of Economics
Slides
MIT
Sep 6, 2019
Statistics and Stochastics Seminar Series, IDSS
UChicago
May 1, 2019
Machine Learning Seminar, TTIC
CREST
Mar 25, 2019
Statistics Seminar, ENSAE-CREST

Teaching

Booth:

Wharton:

  • 622 (MBA): Advanced Quantitative Modeling: Spring 15, Spring 14

Professional Service

Awards

  • George C. Tiao Faculty Fellowship, 2017-now
    for research in computational and data science

  • J. Parker Memorial Bursk Award, 2016
    for excellence in research

  • US Junior Oberwolfach Fellow, 2015

  • Winkelman Fellowship, 2014-2017
    the highest honorific fellowship awarded by the Wharton School

Tags

Contact