3 papers
stat.ML2026
Forecast collapse of transformer-based models under squared loss in financial time series
Pierre Andreoletti
We study trajectory forecasting under squared loss for time series with weak conditional structure, using highly expressive prediction models. Building on the classical characteriz…
math.PR2025
Sub-diffusive behavior of a recurrent Axis-Driven Random Walk
Pierre Andreoletti, Pierre Debs
We study the second order of the number of excursions of a simple random walk with a bias that drives a return toward the origin along the axes introduced by P. Andreoletti and P.…
math.PR2024
Axis-Driven Random Walks on (transient cases)
Pierre Andreoletti
Axis-driven random walks were introduced by P. Andreoletti and P. Debs [AD23] to provide a rough description of the behaviour of a particle trapped in a localized force field. In c…