Tam Le
@ntamle.bsky.social
Assistant professor at Université Paris Cité - LPSM. Working on optimization and machine learning.
For instance, if a critical point is flat, it may be more sensible to errors, since the vanishing gradient cannot compensate the perturbations. We thus obtain an estimate (rho) of the fluctuations around the critical set, depending on the coefficients theta and beta.
June 5, 2025 at 6:23 AM
For instance, if a critical point is flat, it may be more sensible to errors, since the vanishing gradient cannot compensate the perturbations. We thus obtain an estimate (rho) of the fluctuations around the critical set, depending on the coefficients theta and beta.
The idea of the analysis was to quantify how much critical points are flat or sharp. So we relied on KL inequality and a metric subregularity condition. They are satisfied for a large class of functions called "definable" or semialgebraic ones (say, piecewise polynomial).
June 5, 2025 at 6:19 AM
The idea of the analysis was to quantify how much critical points are flat or sharp. So we relied on KL inequality and a metric subregularity condition. They are satisfied for a large class of functions called "definable" or semialgebraic ones (say, piecewise polynomial).