6 papers
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…
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…
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…
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…
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…
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…