activity
20242026
collaborators

6 papers

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…

cs.LG2026

Latent Structure Emergence in Diffusion Models via Confidence-Based Filtering

Wei Wei, Yizhou Zeng, Kuntian Chen +3

Diffusion models rely on a high-dimensional latent space of initial noise seeds, yet it remains unclear whether this space contains sufficient structure to predict properties of th…

math.ST2026

Optimal neural network approximation of smooth compositional functions on sets with low intrinsic dimension

Thomas Nagler, Sophie Langer

We study approximation and statistical learning properties of deep ReLU networks under structural assumptions that mitigate the curse of dimensionality. We prove minimax-optimal un…

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…

math.OC2025

Accelerated Mirror Descent for Non-Euclidean Star-convex Functions

Clement Lezane, Sophie Langer, Wouter M Koolen

Acceleration for non-convex functions is a fundamental challenge in optimisation. We revisit star-convex functions, which are strictly unimodal on all lines through a minimizer. [1…

cs.LG2024

On the VC dimension of deep group convolutional neural networks

Anna Sepliarskaia, Sophie Langer, Johannes Schmidt-Hieber

We study the generalization capabilities of Group Convolutional Neural Networks (GCNNs) with ReLU activation function by deriving upper and lower bounds for their Vapnik-Chervonenk…