Virtual

New Technologies in Mathematics Seminar Speaker: Tatsunori Hashimoto, Stanford Title: New directions in synthetic data Abstract: Synthetic data has been an effective, if boring set of techniques: prompt some language model to restructure your corpus to match some downstream task, with occasionally some distillation. In this talk, we will take a more expansive view of […]

New Technologies in Mathematics Seminar Speaker: Pierfrancesco Urbani, Universite Paris-Saclay, CNRS, CEA, Institut de physique theorique Title: Separation of timescales controls feature learning and overfitting in large neural networks Abstract: To understand the inductive bias and generalization capabilities of large, overparameterized machine learning models, it is essential to analyze the dynamics of their training algorithms. […]