arXiv AI June 9, 2026 By Mark Kozdoba, Shie Mannor

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs

arXiv:2606. 08218v1 Announce Type: cross Abstract: Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are a canonical example.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

multimodal

arXiv Machine Learning

Jun 9

Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation

arXiv:2606. 07931v1 Announce Type: cross Abstract: We prove a variance-aware pointwise majorizing-measure theorem for centered Gaussian processes.

By Yunbei Xu

arXiv Machine Learning

Jun 25

An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processes

arXiv:2606. 25882v1 Announce Type: new Abstract: DGPs are probabilistic models with remarkable prediction performance that concatenate GPs across several layers.

By Francisco Javier S\'aez-Maldonado, Juan Maro\~nas, Daniel Hern\'andez-Lobato

arXiv Machine Learning

Jun 3

Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification

arXiv:2510. 02779v4 Announce Type: replace Abstract: Recent advances have significantly improved our understanding of the generalization performance of gradient descent (GD) methods in deep neural networks.

By Yuanfan Li, Yunwen Lei, Zheng-Chu Guo, Yiming Ying

arXiv Machine Learning

Sep 21

Sparse Priors for Efficient Distribution Learning

arXiv:2609. 20883v1 Announce Type: new Abstract: Despite the widespread use and success of generative AI techniques today, theoretical guarantees on learning a distribution supported in $d$ dimensions from $n$ samples degrade as $O(n^{-1/\Theta(d)})$, though shown to be minimax optimal.

By Saumya Goyal, Barnab\'as P\'oczos

efficiency

arXiv Machine Learning

Jun 3

Scalable Derivative Gaussian Processes via Exact Gradient Reduction

arXiv:2606. 02909v1 Announce Type: cross Abstract: Gradient observations can substantially improve Gaussian process (GP) surrogates, particularly in high-dimensional settings where function evaluations are expensive.

By Hyunseok Seung, Matthias Katzfuss

benchmarks

arXiv Machine Learning

Aug 10

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

arXiv:2409. 18804v3 Announce Type: replace-cross Abstract: Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond.

By Iskander Azangulov, George Deligiannidis, Judith Rousseau

diffusion benchmarks

One email a morning, machine-written

Related stories

Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation

An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processes

Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification

Sparse Priors for Efficient Distribution Learning

Scalable Derivative Gaussian Processes via Exact Gradient Reduction

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions