Prediction-powered inference
Prediction-powered inference is a framework for performing valid statistical inference when
an experimental dataset is supplemented with predictions from a machine-learning system …
an experimental dataset is supplemented with predictions from a machine-learning system …
Adaptive and robust multi-task learning
Adaptive and robust multi-task learning Page 1 The Annals of Statistics 2023, Vol. 51, No. 5,
2015–2039 https://doi.org/10.1214/23-AOS2319 © Institute of Mathematical Statistics, 2023 …
2015–2039 https://doi.org/10.1214/23-AOS2319 © Institute of Mathematical Statistics, 2023 …
Learning from similar linear representations: Adaptivity, minimaxity, and robustness
Representation multi-task learning (MTL) has achieved tremendous success in practice.
However, the theoretical understanding of these methods is still lacking. Most existing …
However, the theoretical understanding of these methods is still lacking. Most existing …
Doubly high-dimensional contextual bandits: An interpretable model for joint assortment-pricing
Key challenges in running a retail business include how to select products to present to
consumers (the assortment problem), and how to price products (the pricing problem) to …
consumers (the assortment problem), and how to price products (the pricing problem) to …
COMMUTE: communication-efficient transfer learning for multi-site risk prediction
Objectives: We propose a communication-efficient transfer learning approach (COMMUTE)
that effectively incorporates multi-site healthcare data for training a risk prediction model in a …
that effectively incorporates multi-site healthcare data for training a risk prediction model in a …
Speed up the cold-start learning in two-sided bandits with many arms
Multi-armed bandit (MAB) algorithms are efficient approaches to reduce the opportunity cost
of online experimentation and are used by companies to find the best product from …
of online experimentation and are used by companies to find the best product from …
Estimation and inference for transfer learning with high-dimensional quantile regression
J Huang, M Wang, Y Wu - arxiv preprint arxiv:2211.14578, 2022 - arxiv.org
Transfer learning has become an essential technique to exploit information from the source
domain to boost performance of the target task. Despite the prevalence in high-dimensional …
domain to boost performance of the target task. Despite the prevalence in high-dimensional …
Transportability for bandits with data from different environments
A unifying theme in the design of intelligent agents is to efficiently optimize a policy based on
what prior knowledge of the problem is available and what actions can be taken to learn …
what prior knowledge of the problem is available and what actions can be taken to learn …
Collaborative learning of discrete distributions under heterogeneity and communication constraints
In modern machine learning, users often have to collaborate to learn distributions that
generate the data. Communication can be a significant bottleneck. Prior work has studied …
generate the data. Communication can be a significant bottleneck. Prior work has studied …
Transfer learning for mortality risk: A case study on the United Kingdom
This study introduces a transfer learning framework to address data scarcity in mortality risk
prediction for the UK, where local mortality data is unavailable. By leveraging a pretrained …
prediction for the UK, where local mortality data is unavailable. By leveraging a pretrained …