no code implementations • 1 Apr 2024 • Yue Sun, Chao Chen, Yuesheng Xu, Sihong Xie, Rick S. Blum, Parv Venkitasubramaniam
We theoretically derive conditions where GCNs incorporating such domain differential equations are robust to mismatched training and testing data compared to baseline domain agnostic models.
no code implementations • 22 Mar 2024 • Rui Xu, Yue Sun, Chao Chen, Parv Venkitasubramaniam, Sihong Xie
Uncertainty is critical to reliable decision-making with machine learning.
no code implementations • 9 Feb 2024 • Ce Feng, Parv Venkitasubramaniam
In this context, implementing machine learning (ML) models with real-valued weight parameters can prove to be impractical particularly for large models, and there is a need to train models with quantized discrete weights.
no code implementations • 6 Dec 2023 • Xiaoyu Ge, Kamelia Norouzi, Faegheh Moazeni, Mirel Sehic, Javad Khazaei, Parv Venkitasubramaniam, Rick Blum
Cybersecurity in building energy management is crucial for protecting infrastructure, ensuring data integrity, and preventing unauthorized access or manipulation.
no code implementations • 25 Jul 2023 • Ce Feng, Nuo Xu, Wujie Wen, Parv Venkitasubramaniam, Caiwen Ding
In particular, for fully connected layers, we combine a block-circulant based spatial restructuring with Spectral-DP to achieve better utility.
1 code implementation • 11 Jun 2022 • Nuo Xu, Binghui Wang, Ran Ran, Wujie Wen, Parv Venkitasubramaniam
Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training.
no code implementations • 6 May 2021 • Nayara Aguiar, Parv Venkitasubramaniam, Vijay Gupta
For a duopoly in which agents are coupled in their payments, we show that if the principal and the agents interact finitely many times, the agents can derive rent by colluding even if the principal knows the types of the agents.
no code implementations • 27 Sep 2019 • Kostas Hatalis, Parv Venkitasubramaniam, Shalinee Kishore
In future smart grids, certain portions of a customers load usage could be under automatic control with a cyber-enabled DSM program which selectively schedules loads as a function of electricity prices to improve power balance and grid stability.