Showing math.PRShow all
2 papers · 1 filter
math.PR2025
A theoretical basis for model collapse in recursive training
Vivek Shripad Borkar
It is known that recursive training from generative models can lead to the so called `collapse' of the simulated probability distribution. This note shows that one in fact gets two…
math.PR2024
Stochastic Approximation with Two Time Scales: The General Case
Vivek S Borkar
Two time scale stochastic approximation is analyzed when the iterates on either or both time scales do not necessarily converge.