2 papers
stat.ML2026
Uniform Scaling Limits in AdamW-Trained Transformers
William Gibson, Christoph Reisinger
We study the large-depth limit of transformers trained with AdamW, by modelling the hidden-state dynamics as an interacting particle system (IPS) coupled through the attention mech…
math.PR2025
Milstein-type schemes for McKean-Vlasov SDEs driven by Brownian motion and Poisson random measure (with super-linear coefficients)
Sani Biswas, Chaman Kumar, Christoph Reisinger +1
In this work, we present a general Milstein-type scheme for McKean-Vlasov stochastic differential equations (SDEs) driven by Brownian motion and Poisson random measure and the asso…