autoregressive diffusion models

Jane Street has published a blog post asking whether autoregressive diffusion models can be used to generate synthetic market data. The piece, written by an employee, examines how generative techniques borrowed from machine learning might reproduce the statistical behaviour of financial time series. Readers in quantitative finance and ML circles are discussing the approach and its practical limits.

Trading firm Jane Street has published a blog post examining whether autoregressive diffusion models can be used to generate synthetic market data. The piece walks through how these generative models, best known for image and text generation, might produce realistic financial time series. It is drawing attention among machine learning practitioners and quants discussing generative approaches to market simulation.