About
I am an Associate Professor of Statistics at Rutgers University. I received my Ph.D. in Statistics from the University of Washington in 2018 under the supervision of Professor Jon A. Wellner.
I work on the mathematical foundations of statistical inference and learning, with broad interests in empirical process theory, nonparametric inference, mean-field high-dimensional statistics, and large random iterative algorithms. My current research focuses on understanding the precise dynamics of modern learning algorithms, including nonconvex and sequential methods, and their implications for statistical inference, using tools from high-dimensional probability, optimization, and statistical physics.
I currently serve as an Associate Editor for Bernoulli, and my research is supported by the NSF through a CAREER Award.
Papers
-
Q. Han and M. Imaizumi. Precise gradient descent training dynamics for finite-width multi-layer neural networks.
-
Q. Han and X. Xu. Gradient descent inference in empirical risk minimization. Ann. Statist., to appear.
-
Q. Han, K. Khamaru and C.-H. Zhang. UCB algorithms for multi-arm bandits: precise regret and adaptive inference.
-
Q. Han. Entrywise dynamics and universality for general first order methods. Ann. Statist., 53, 1783-1807.
-
Z. Bao, Q. Han and X. Xu. A leave-one-out approach to approximate message passing. Ann. Appl. Probab., 35, 2716-2766.
-
Q. Han and X. Xu. The distribution of Ridgeless least squares interpolators. J. Mach. Learn. Res., 27 (23), 1-94.
-
Q. Han and H. Ren. Gaussian random projections of convex cones: approximate kinematic formulae and applications. Inf. Inference, 15, iaag006.
-
Q. Han and Y. Shen. Universality of regularized regression estimators in high dimensions. Ann. Statist., 51, 1799-1823.
-
Q. Han. Noisy linear inverse problems under convex constraints: exact risk asymptotics in high dimensions. Ann. Statist., 51, 1611-1638.
-
Q. Han and Y. Shen. Generalized kernel distance covariance in high dimensions: Non-null CLTs and power universality. Inf. Inference, 13, iaae017.
-
*O. Y. Feng, Y. Chen, Q. Han, R. J. Carroll and R. J. Samworth. Nonparametric, tuning-free estimation of S-shaped functions. J. Roy. Statist. Soc., Ser. B, 84, 1324-1352.
-
Q. Han, T. Jiang and Y. Shen. Contiguity under high dimensional Gaussianity with applications to covariance testing. Ann. Appl. Probab., 33, 4272-4321.
-
Q. Han, B. Sen and Y. Shen. High dimensional asymptotics of likelihood ratio tests in the Gaussian sequence model under convex constraints. Ann. Statist., 50, 376-406.
-
H. Deng, Q. Han and B. Sen. Inference for local parameters in convexity constrained models. J. Amer. Statist. Assoc., 118, 2721-2735.
-
*Y. Shen, Q. Han and F. Han. On a phase transition in general order spline regression. IEEE Trans. Inform. Theory, 68, 4043-4069.
-
H. Deng, Q. Han and C.-H. Zhang. Confidence intervals for multiple isotonic regression and other monotone models. Ann. Statist., 49, 2021-2052.
-
Q. Han and K. Kato. Berry-Esseen bounds for Chernoff-type non-standard asymptotics in isotonic regression. Ann. Appl. Probab., 32, 1459-1498.
-
Q. Han. Set structured global empirical risk minimizers are rate optimal in general dimensions. Ann. Statist., 49, 2642-2671.
-
Q. Han. Multiplier U-processes: sharp bounds and applications. Bernoulli, 28, 87-124.
-
Q. Han and J. A. Wellner. Complex sampling designs: uniform limit theorems and applications. Ann. Statist., 49, 459-485.
-
Q. Han and C.-H. Zhang. Limit distribution theory for block estimators in multiple isotonic regression. Ann. Statist., 48, 3251-3282.
-
Q. Han and J. A. Wellner. Robustness of shape-restricted regression estimators: an envelope perspective.
-
*Q. Han, *T. Wang, S. Chatterjee and R. J. Samworth. Isotonic regression in general dimensions. Ann. Statist., 47, 2440-2471.
-
Q. Han and J. A. Wellner. Convergence rates of least squares regression estimators with heavy-tailed errors. Ann. Statist., 47, 2286-2319.
-
Q. Han. Oracle posterior contraction rates under hierarchical priors. Electron. J. Statist., 15, 1085-1153.
-
Q. Han and J. A. Wellner. Multivariate convex regression: global risk bounds and adaptation.
-
Q. Han and J. A. Wellner. Approximation and estimation of s-concave densities via Rényi divergences. Ann. Statist., 44, 1332-1359.
-
*A. Jalali, Q. Han, I. Dumitriu and M. Fazel. Exploiting tradeoffs for exact recovery in heterogeneous stochastic block models. NeurIPS 2016, 29.