3 papers
cs.LG2026
Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice
Ziqi Zhao, Jialin Lu, Junjie Shan +3
Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setting, the initiator can withho…
stat.ML2025
Statistical Properties of Deep Neural Networks with Dependent Data
Chad Brown
This paper establishes statistical properties of deep neural network (DNN) estimators under dependent data. Two general results for nonparametric sieve estimators directly applicab…
econ.EM2024
Inference in Partially Linear Models under Dependent Data with Deep Neural Networks
Chad Brown
I consider inference in a partially linear regression model under stationary -mixing data after first stage deep neural network (DNN) estimation. Using the DNN results of Brown…