Distribution shifts are a serious concern in modern statistical learning...
Randomized algorithms, such as randomized sketching or projections, are ...
Statistical machine learning methods often face the challenge of limited...
We propose a new method for high-dimensional semi-supervised learning
pr...
We introduce Joint Coverage Regions (JCRs), which unify confidence inter...
A flexible method is developed to construct a confidence interval for th...
To infer the treatment effect for a single treated unit using panel data...
Uncertainty quantification is a key component of machine learning models...
We consider the problem of learning discriminative representations for d...
We introduce a unified framework for group equivariant networks on
homog...
The performance of machine learning models can significantly degrade und...
Anomaly detection is essential for preventing hazardous outcomes for
saf...
Increasing concerns about disparate effects of AI have motivated a great...
We propose the first SE(3)-equivariant coordinate-based network for lear...
Predicting sets of outcomes – instead of unique outcomes – is a promisin...
Environments with sparse rewards and long horizons pose a significant
ch...
Machine learning algorithms are becoming integrated into more and more
h...
Machine learning methods such as deep neural networks (DNNs), despite th...
Adapting to the structure of data distributions (such as symmetry and
tr...
There has been a growing need to provide Byzantine-resilience in distrib...
Modern methods for learning from data depend on many tuning parameters, ...
An important challenge facing modern machine learning is how to rigorous...
Invariance-based randomization tests – such as permutation tests – are a...
Adversarially trained models exhibit a large generalization gap: they ca...
Dimensionality reduction via PCA and factor analysis is an important too...
For a tall n× d matrix A and a random m× n sketching matrix
S, the sketc...
Modern machine learning methods are often overparametrized, allowing
ada...
Machine learning models are not static and may need to be retrained on
s...
In our "big data" age, the size and complexity of data is steadily
incre...
We study the implicit regularization of mini-batch stochastic gradient
d...
We provide an exact analysis of the limiting spectrum of matrices random...
Normalization methods such as batch normalization are commonly used in
o...
We study the following three fundamental problems about ridge regression...
Many complex deep learning models have found success by exploiting symme...
In many areas, practitioners need to analyze large datasets that challen...
Large datasets create opportunities as well as analytic challenges. A re...
Modern massive datasets pose an enormous computational burden to
practit...
Drawing statistical inferences from large datasets in a model-robust way...
Modern high-throughput science often leads to multiple testing problems:...
Factor analysis is widely used in many application areas. The first step...