Upcoming talks

• September 21st 2026, 11:30 p.m. Room 012 Centro Didattico Morgagni, Sara Shashaani (Associate Professor at North Carolina State University)

Title: Adaptive Sampling and Regularization for Stochastic Trust-region Methods

Abstract: Trust-region methods have proven highly effective for unconstrained nonconvex stochastic optimization problems where objective and gradient information are available only through noisy stochastic oracles. ASTRO is a class of adaptive sampling trust-region methods that dynamically determine sampling effort while constructing local quadratic models from noisy function and gradient observations. By exploiting dependence among samples and the stochastic structure of the problem, ASTRO achieves strong convergence and complexity guarantees. Its derivative-free variant, ASTRO-DF, relies solely on noisy function evaluations and also enjoys almost-sure convergence guarantees.