322 citations · 915 across the 42 of their papers we have counts for
5 papers · 1 filter
Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
Luca Eyring, Dominik Klein, Théo Uscidda +4
In optimal transport (OT), a Monge map is known as a mapping that transports a source distribution to a target distribution in the most cost-efficient way. Recently, multiple neura…
ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
Stéphane d'Ascoli, Sören Becker, Alexander Mathis +2
We introduce ODEFormer, the first transformer able to infer multidimensional ordinary differential equation (ODE) systems in symbolic form from the observation of a single solution…
Predicting Ordinary Differential Equations with Transformers
Sören Becker, Michal Klein, Alexander Neitz +2
We develop a transformer-based sequence-to-sequence model that recovers scalar ordinary differential equations (ODEs) in symbolic form from irregularly sampled and noisy observatio…
Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints
Alistair White, Niki Kilbertus, Maximilian Gelbrecht +1
Many successful methods to learn dynamical systems from data have recently been introduced. However, ensuring that the inferred dynamics preserve known constraints, such as conserv…
Sequential Underspecified Instrument Selection for Cause-Effect Estimation
Elisabeth Ailer, Jason Hartford, Niki Kilbertus
Instrumental variable (IV) methods are used to estimate causal effects in settings with unobserved confounding, where we cannot directly experiment on the treatment variable. Instr…