3 papers
cs.LG2026
Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection
Guillaume Coulaud, Reza Akbarinia, Florent Masseglia
Reconstruction-based methods are widely used for time series anomaly detection, where models are trained to reconstruct subsequences, and anomalies are identified through reconstru…
stat.ML2026
TRAKNN: Efficient Trajectory Aware Spatiotemporal kNN for Rare Meteorological Trajectory Detection
Guillaume Coulaud, Davide Faranda
Extreme weather events, such as windstorms and heatwaves, are driven by persistent atmospheric circulation patterns that evolve over several consecutive days. While traditional cir…
math.AP2024
Investigations on Physics-Informed Neural Networks for Aerodynamics
Guillaume Coulaud, Maxime Le, Régis Duvigneau
Physics-Informed Neural Networks (PINNs) have recently emerged as a novel approach to simulate complex physical systems on the basis of both data observations and physical models.…