60 citations · 111 across the 14 of their papers we have counts for
22 papers
High-dimensional sparsity-adaptive multiple change-point detection
Hyeyoung Maeng, Tengyao Wang, Piotr Fryzlewicz
We introduce a method for detecting multiple change-points in the mean of a high-dimensional data sequence. Unlike existing top-down (i.e. divisive) algorithms, we adopt a bottom-u…
Optimal In-context Adaptivity and Distributional Robustness of Transformers
Tianyi Ma, Tengyao Wang, Richard J. Samworth
We study in-context learning problems where a Transformer is pretrained on tasks drawn from a mixture distribution , called the pretraining prior,…
Deep learning with missing data
Tianyi Ma, Tengyao Wang, Richard J. Samworth
In the context of multivariate nonparametric regression with missing covariates, we propose Pattern Embedded Neural Networks (PENNs), which can be applied in conjunction with any e…
Estimation beyond Missing (Completely) at Random
Tianyi Ma, Kabir A. Verchand, Thomas B. Berrett +2
We study the effects of missingness on the estimation of population parameters. Moving beyond restrictive missing completely at random (MCAR) assumptions, we first formulate a miss…
SpreadDetect: Detection of spreading change in a network over time
Hanqing Cai, Tengyao Wang
Change-point analysis has been successfully applied to the detect changes in multivariate data streams over time. In many applications, when data are observed over a graph/network,…
Robust mean change point testing in high-dimensional data with heavy tails
Mengchu Li, Yudong Chen, Tengyao Wang +1
We study mean change point testing problems for high-dimensional data, with exponentially- or polynomially-decaying tails. In each case, depending on the -norm of the mean…
Sharp-SSL: Selective high-dimensional axis-aligned random projections for semi-supervised learning
Tengyao Wang, Edgar Dobriban, Milana Gataric +1
We propose a new method for high-dimensional semi-supervised learning problems based on the careful aggregation of the results of a low-dimensional procedure applied to many axis-a…
Sparse change detection in high-dimensional linear regression
Fengnan Gao, Tengyao Wang
We introduce a new methodology 'charcoal' for estimating the location of sparse changes in high-dimensional linear regression coefficients, without assuming that those coefficients…
Inference in high-dimensional online changepoint detection
Yudong Chen, Tengyao Wang, Richard J. Samworth
We introduce and study two new inferential challenges associated with the sequential detection of change in a high-dimensional mean vector. First, we seek a confidence interval for…
High-dimensional changepoint estimation with heterogeneous missingness
Bertille Follain, Tengyao Wang, Richard J. Samworth
We propose a new method for changepoint estimation in partially-observed, high-dimensional time series that undergo a simultaneous change in mean in a sparse subset of coordinates.…
Estimation of high-dimensional change-points under a group sparsity structure
Hanqing Cai, Tengyao Wang
Change-points are a routine feature of 'big data' observed in the form of high-dimensional data streams. In many such data streams, the component series possess group structures an…
AIM 2020 Challenge on Rendering Realistic Bokeh
Andrey Ignatov, Radu Timofte, Ming Qian +32
This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solvin…
Two-sample testing of high-dimensional linear regression coefficients via complementary sketching
Fengnan Gao, Tengyao Wang
We introduce a new method for two-sample testing of high-dimensional linear regression coefficients without assuming that those coefficients are individually estimable. The procedu…
High-dimensional, multiscale online changepoint detection
Yudong Chen, Tengyao Wang, Richard J. Samworth
We introduce a new method for high-dimensional, online changepoint detection in settings where a -variate Gaussian data stream may undergo a change in mean. The procedure works…
High-dimensional principal component analysis with heterogeneous missingness
Ziwei Zhu, Tengyao Wang, Richard J. Samworth
We study the problem of high-dimensional Principal Component Analysis (PCA) with missing observations. In simple, homogeneous missingness settings with a noise level of constant or…
Sparse principal component analysis via axis-aligned random projections
Milana Gataric, Tengyao Wang, Richard J. Samworth
We introduce a new method for sparse principal component analysis, based on the aggregation of eigenvector information from carefully-selected axis-aligned random projections of th…
Isotonic regression in general dimensions
Qiyang Han, Tengyao Wang, Sabyasachi Chatterjee +1
We study the least squares regression function estimator over the class of real-valued functions on that are increasing in each coordinate. For uniformly bounded signals…
High-dimensional changepoint estimation via sparse projection
Tengyao Wang, Richard J. Samworth
Changepoints are a very common feature of Big Data that arrive in the form of a data stream. In this paper, we study high-dimensional time series in which, at certain time points,…
Average-case Hardness of RIP Certification
Tengyao Wang, Quentin Berthet, Yaniv Plan
The restricted isometry property (RIP) for design matrices gives guarantees for optimal recovery in sparse linear models. It is of high interest in compressed sensing and statistic…
Statistical and computational trade-offs in estimation of sparse principal components
Tengyao Wang, Quentin Berthet, Richard J. Samworth
In recent years, sparse principal component analysis has emerged as an extremely popular dimension reduction technique for high-dimensional data. The theoretical challenge, in the…
A useful variant of the Davis--Kahan theorem for statisticians
Yi Yu, Tengyao Wang, Richard J. Samworth
The Davis--Kahan theorem is used in the analysis of many statistical procedures to bound the distance between subspaces spanned by population eigenvectors and their sample versions…
Multiple Identifications in Multi-Armed Bandits
Sébastien Bubeck, Tengyao Wang, Nitin Viswanathan
We study the problem of identifying the top arms in a multi-armed bandit game. Our proposed solution relies on a new algorithm based on successive rejects of the seemingly bad…