3 papers
stat.ML2026
Modular Bayesian Foundation Models: Bayesian time series encoders for OOD detection, routing and forecasting
Mame Diarra Toure, Quang Hung Pham, Mohamed Ryad Zemouri +3
Industrial systems continuously generate time series that vary in sampling frequency, scale, dynamics, and operating regime. Consequently a single time-series foundation model may…
stat.ML2026
Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions
Mame Diarra Toure, David A. Stephens
In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI…
stat.ML2026
Singular Bayesian Neural Networks
Mame Diarra Toure, David A. Stephens
Bayesian neural networks promise calibrated uncertainty but require parameters for standard mean-field Gaussian posteriors. We argue this cost is often unnecessary, particu…