166 citations · 595 across the 71 of their papers we have counts for
11 papers · 1 filter
SymmPI: Predictive Inference for Data with Group Symmetries
Edgar Dobriban, Mengxin Yu
Quantifying the uncertainty of predictions is a core problem in modern statistics. Methods for predictive inference have been developed under a variety of assumptions, often -- for…
PAC Prediction Sets Under Label Shift
Wenwen Si, Sangdon Park, Insup Lee +2
Prediction sets capture uncertainty by predicting sets of labels rather than individual labels, enabling downstream decisions to conservatively account for all plausible outcomes.…
Jailbreaking Black Box Large Language Models in Twenty Queries
Patrick Chao, Alexander Robey, Edgar Dobriban +3
There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, whic…
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
Behrad Moniri, Donghwan Lee, Hamed Hassani +1
Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks u…
Minimax Statistical Estimation under Wasserstein Contamination
Patrick Chao, Edgar Dobriban
Contaminations are a key concern in modern statistical learning, as small but systematic perturbations of all datapoints can substantially alter estimation results. Here, we study…
Statistical inference in two-stage observation models including algorithmic randomness
Zhixiang Zhang, Sokbae Lee, Edgar Dobriban
Randomized algorithms, such as random sampling, random projections, and stochastic optimization, are increasingly used to reduce the computational cost of modern statistical analys…
Efficient and Multiply Robust Risk Estimation under General Forms of Dataset Shift
Hongxiang Qiu, Eric Tchetgen Tchetgen, Edgar Dobriban
Statistical machine learning methods often face the challenge of limited data available from the population of interest. One remedy is to leverage data from auxiliary source popula…
Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity
Xinmeng Huang, Kan Xu, Donghwan Lee +3
Large and complex datasets are often collected from several, possibly heterogeneous sources. Multitask learning methods improve efficiency by leveraging commonalities across datase…
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…
Joint Coverage Regions: Simultaneous Confidence and Prediction Sets
Edgar Dobriban, Zhanran Lin
We introduce Joint Coverage Regions (JCRs), which unify confidence intervals and prediction regions in frequentist statistics. Specifically, joint coverage regions aim to cover a p…
Demystifying Disagreement-on-the-Line in High Dimensions
Donghwan Lee, Behrad Moniri, Xinmeng Huang +2
Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along w…