Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems
This work addresses the challenge of modeling multi-modal transitions in stochastic physical systems, offering a simple and efficient alternative to ensemble or latent variable methods.
Stochastic Lifting introduces a method to generate diverse trajectories for stochastic physical systems by attaching random labels to state transitions, avoiding mean collapse and enabling single-network evaluation per time step.
Many stochastic physical systems evolve smoothly over time in the sense that the distribution of states changes regularly across time steps. The transition from current state to the next state can often be modeled as the combination of a smooth map and an explicit source of randomness. Stochastic Lifting exploits this structure by attaching an independent, high-dimensional random label to each state transition in the training data and fitting a transition map from the current state and label to the next state using a standard regression loss. The labels act as auxiliary coordinates that let the model represent multiple plausible next states from similar current states, avoiding collapse to a mean prediction in the finite-sample size regime. At inference, fresh labels are sampled at each time step and the learned map is rolled forward autoregressively, generating diverse trajectories with a single network evaluation per time step.