48 citations · 175 across the 26 of their papers we have counts for
4 papers · 1 filter
Information-Theoretic Proofs for Diffusion Sampling
Galen Reeves, Henry D. Pfister
This paper provides an elementary, self-contained analysis of diffusion-based sampling methods for generative modeling. In contrast to existing approaches that rely on continuous-t…
Approximate Message Passing for the Matrix Tensor Product Model
Riccardo Rossetti, Galen Reeves
We propose and analyze an approximate message passing (AMP) algorithm for the matrix tensor product model, which is a generalization of the standard spiked matrix models that allow…
Fundamental limits for rank-one matrix estimation with groupwise heteroskedasticity
Joshua K. Behne, Galen Reeves
Low-rank matrix recovery problems involving high-dimensional and heterogeneous data appear in applications throughout statistics and machine learning. The contribution of this pape…
The Gaussian equivalence of generative models for learning with shallow neural networks
Sebastian Goldt, Bruno Loureiro, Galen Reeves +3
Understanding the impact of data structure on the computational tractability of learning is a key challenge for the theory of neural networks. Many theoretical works do not explici…