Forking uncertainties: Reliable prediction and model predictive control with sequence models via conformal risk control
In many real-world problems, predictions are leveraged to monitor and control cyber-
physical systems, demanding guarantees on the satisfaction of reliability and safety …
physical systems, demanding guarantees on the satisfaction of reliability and safety …
Robust Bayesian learning for reliable wireless AI: Framework and applications
This work takes a critical look at the application of conventional machine learning methods
to wireless communication problems through the lens of reliability and robustness. Deep …
to wireless communication problems through the lens of reliability and robustness. Deep …
Calibrating AI models for wireless communications via conformal prediction
When used in complex engineered systems, such as communication networks, artificial
intelligence (AI) models should be not only as accurate as possible, but also well calibrated …
intelligence (AI) models should be not only as accurate as possible, but also well calibrated …
Improving robust generalization by direct pac-bayesian bound minimization
Recent research in robust optimization has shown an overfitting-like phenomenon in which
models trained against adversarial attacks exhibit higher robustness on the training set …
models trained against adversarial attacks exhibit higher robustness on the training set …
Quantum conformal prediction for reliable uncertainty quantification in quantum machine learning
Quantum machine learning is a promising programming paradigm for the optimization of
quantum algorithms in the current era of noisy intermediate-scale quantum computers. A …
quantum algorithms in the current era of noisy intermediate-scale quantum computers. A …
Calibration-aware bayesian learning
Deep learning models, including modern systems like large language models, are well
known to offer unreliable estimates of the uncertainty of their decisions. In order to improve …
known to offer unreliable estimates of the uncertainty of their decisions. In order to improve …
Security-preserving federated learning via byzantine-sensitive triplet distance
While being an effective framework of learning a shared model across multiple edge
devices, federated learning (FL) is generally vulnerable to Byzantine attacks from …
devices, federated learning (FL) is generally vulnerable to Byzantine attacks from …
On the temperature of bayesian graph neural networks for conformal prediction
Accurate uncertainty quantification in graph neural networks (GNNs) is essential, especially
in high-stakes domains where GNNs are frequently employed. Conformal prediction (CP) …
in high-stakes domains where GNNs are frequently employed. Conformal prediction (CP) …
Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference
The application of artificial intelligence (AI) models in fields such as engineering is limited by
the known difficulty of quantifying the reliability of an AI's decision. A well-calibrated AI model …
the known difficulty of quantifying the reliability of an AI's decision. A well-calibrated AI model …
Calibrating AI models for few-shot demodulation VIA conformal prediction
Artificial Intelligent (AI) tools can be useful to address model deficits in the design of
communication systems. However, conventional learning-based AI algorithms yield poorly …
communication systems. However, conventional learning-based AI algorithms yield poorly …