7 papers
GradInf: Gradient Estimation as Probabilistic Inference
Gaurav Arya, Mathieu Huot, Moritz Schauer +2
Gradient estimation -- the task of computing the gradient of the expected value of a probabilistic program -- has diverse applications in scientific computing, but is notoriously d…
Causality--Δ: Jacobian-Based Dependency Analysis in Flow Matching Models
Reza Rezvan, Gustav Gille, Moritz Schauer +1
Flow matching learns a velocity field that transports a base distribution to data. We study how small latent perturbations propagate through these flows and show that Jacobian-vect…
Controlled stochastic processes for simulated annealing
Vincent Molin, Axel Ringh, Moritz Schauer +1
Simulated annealing solves global optimization problems by means of a random walk in a cooling energy landscape based on the objective function and a temperature parameter. However…
Rebalancing Markov jump processes for non-reversible continuous-time sampling
Erik Jansson, Moritz Schauer, Ruben Seyer +1
Markov chain Monte Carlo methods are central in computational statistics, and typically rely on detailed balance to ensure invariance with respect to a target distribution. Althoug…
Guided smoothing and control for diffusion processes
Oskar Eklund, Annika Lang, Moritz Schauer
The smoothing distribution is the conditional distribution of the diffusion process in the space of trajectories given noisy observations made continuously in time. It is generally…
Gradient Estimation via Differentiable Metropolis-Hastings
Gaurav Arya, Moritz Schauer, Ruben Seyer
Metropolis-Hastings estimates intractable expectations - can differentiating the algorithm estimate their gradients? The challenge is that Metropolis-Hastings trajectories are not…
Causal structure learning with momentum: Sampling distributions over Markov Equivalence Classes of DAGs
Moritz Schauer, Marcel Wienöbst
In the context of inferring a Bayesian network structure (directed acyclic graph, DAG for short), we devise a non-reversible continuous time Markov chain, the ``Causal Zig-Zag samp…