Search Results for author:
Found 8 papers, 1 papers with code
Incorporating Domain Differential Equations into Graph Convolutional Networks to Lower Generalization Discrepancy
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.
Robust Conformal Prediction under Distribution Shift via Physics-Informed Structural Causal Model
Uncertainty is critical to reliable decision-making with machine learning.
RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
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.
Vulnerability of Building Energy Management against Targeted False Data Injection Attacks:Model Predictive Control vs. Proportional Integral
Cybersecurity in building energy management is crucial for protecting infrastructure, ensuring data integrity, and preventing unauthorized access or manipulation.
Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filtering
In particular, for fully connected layers, we combine a block-circulant based spatial restructuring with Spectral-DP to achieve better utility.
NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks
Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training.
Data-Driven Contract Design for Multi-Agent Systems with Collusion Detection
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.
Modeling and Detection of Future Cyber-Enabled DSM Data Attacks using Supervised Learning
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.
