Joshua DeOliveira

According to our database, Joshua DeOliveira authored at least 6 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Neural Tangent Kernels Under Stochastic Data Augmentation.

Joshua DeOliveira, Sajal Chakroborty, Walter Gerych, Elke A. Rundensteiner

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Agree to Disagree: Robust Anomaly Detection with Noisy Labels.

Dennis M. Hofmann, Peter M. VanNostrand, Lei Ma, Huayi Zhang, Joshua DeOliveira, Lei Cao, Elke A. Rundensteiner

Proc. ACM Manag. Data, February, 2025

The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training.

Joshua DeOliveira, Walter Gerych, Elke A. Rundensteiner

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

GAN Stabilization Under Practical Training Assumptions.

Joshua DeOliveira, Walter Gerych, Elke A. Rundensteiner

Proceedings of the IEEE International Conference on Big Data, 2024

2022

HAR-CTGAN: A Mobile Sensor Data Generation Tool for Human Activity Recognition.

Joshua DeOliveira, Walter Gerych, Aruzhan Koshkarova, Elke A. Rundensteiner, Emmanuel Agu

Proceedings of the IEEE International Conference on Big Data, 2022

2021

GAN for Generating User-Specific Human Activity Data From An Incomplete Training Corpus.

Walter Gerych, Harrison Kim, Joshua DeOliveira, MaryClare Martin, Luke Buquicchio, Kavin Chandrasekaran, Abdulaziz Alajaji, Hamid Mansoor, Elke A. Rundensteiner, Emmanuel Agu

Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021