5 papers
Reflected Schrödinger Bridge Matching
Marcus Häggbom, Viktor Nilsson, Pierre Nyquist +1
Recent advances in generative modeling have enabled the efficient computation of Schrödinger bridges (SB) in high-dimensional settings by leveraging partially simulation-free trai…
Efficient Flow Matching using Latent Variables
Anirban Samaddar, Yixuan Sun, Viktor Nilsson +1
Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explici…
A weak convergence approach to the large deviations of the dynamic Schrödinger problem
Viktor Nilsson, Pierre Nyquist
In this paper, we consider the large deviations for dynamical Schrödinger problems, using the variational approach developed by Dupuis, Ellis, Budhiraja, and others. Recent result…
Large deviations for interacting particle dynamics for finding mixed equilibria in zero-sum games
Viktor Nilsson, Pierre Nyquist
Finding equilibrium points in continuous minmax games has become a key problem within machine learning, in part due to its connection to the training of generative adversarial netw…
Large deviations for scaled families of Schrödinger bridges with reflection
Viktor Nilsson, Pierre Nyquist
In this paper, we show a large deviation principle for certain sequences of static Schrödinger bridges, typically motivated by a scale-parameter decreasing towards zero, extending…