Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
When do explicit penalties improve flow matching?
Lea Kunkel, Alberto González-Sanz, Sophie Langer
Flow matching can learn structure directly from data, raising the question of when additional constraints improve generation. We study penalties that encode such constraints, with…
stat.ML2026
Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under -Mixing
Leon Halgryn, Sophie Langer, Janusz M. Meylahn +1
Finite-sample analyses of deep Q-learning typically treat replayed data as independent, even though it is sampled from temporally dependent state-action trajectories. We study the…
stat.ML2025
On the expressivity of deep Heaviside networks
Insung Kong, Juntong Chen, Sophie Langer +1
We show that deep Heaviside networks (DHNs) have limited expressiveness but that this can be overcome by including either skip connections or neurons with linear activation. We pro…