Archives AI News

A Computable Measure of Suboptimality for Entropy-Regularised Variational Objectives

arXiv:2509.10393v1 Announce Type: cross Abstract: Several emerging post-Bayesian methods target a probability distribution for which an entropy-regularised variational objective is minimised. This increased flexibility introduces a computational challenge, as one loses access to an explicit unnormalised density for the target.…

Sufficient Invariant Learning for Distribution Shift

arXiv:2210.13533v4 Announce Type: replace-cross Abstract: Learning robust models under distribution shifts between training and test datasets is a fundamental challenge in machine learning. While learning invariant features across environments is a popular approach, it often assumes that these features are…

Sparse Polyak: an adaptive step size rule for high-dimensional M-estimation

arXiv:2509.09802v1 Announce Type: cross Abstract: We propose and study Sparse Polyak, a variant of Polyak’s adaptive step size, designed to solve high-dimensional statistical estimation problems where the problem dimension is allowed to grow much faster than the sample size. In…

A Smooth Computational Transition in Tensor PCA

arXiv:2509.09904v1 Announce Type: cross Abstract: We propose an efficient algorithm for tensor PCA based on counting a specific family of weighted hypergraphs. For the order-$p$ tensor PCA problem where $p geq 3$ is a fixed integer, we show that when…

Zero-inflation in the Multivariate Poisson Lognormal Family

arXiv:2405.14711v2 Announce Type: replace-cross Abstract: Analyzing high-dimensional count data is a challenge and statistical model-based approaches provide an adequate and efficient framework that preserves explainability. The (multivariate) Poisson-Log-Normal (PLN) model is one such model: it assumes count data are driven…

Flow Straight and Fast in Hilbert Space: Functional Rectified Flow

arXiv:2509.10384v1 Announce Type: cross Abstract: Many generative models originally developed in finite-dimensional Euclidean space have functional generalizations in infinite-dimensional settings. However, the extension of rectified flow to infinite-dimensional spaces remains unexplored. In this work, we establish a rigorous functional formulation…