Modern data analysis increasingly requires identifying shared latent structure across multiple high-dimensional datasets. A commonly used model assumes that the data matrices are noisy observations of low-rank matrices with a shared singular subspace. In this case, two primary methods have emerged for estimating this s...
Tavor Z. Baharav, Phillip B. Nicol, Rafael A. Irizarry et al.· 0 citations
This paper derives the first upper regret bound that explicitly accounts for changes in the observations sampling frequency and formulates practical recommendations about dataset sizes and stale data policies of TVBO algorithms.
CatSIM uses a structural similarity image quality paradigm and is robust to small perturbations in location so that structures in similar, but not entirely overlapping, regions of two images are rated higher than using simple matching.
Geoffrey Z. Thompson, Ranjan Maitra· arXiv.org· 2 citations
DeepX‐GAN (Dependence‐Enhanced Embedding for Physical eXtremes—Generative Adversarial Network) is introduced, a deep generative model that explicitly captures the spatial structure of rare extremes and enables the simulation of statistically plausible extremes beyond the observed record, evaluated against long climate...
Xin-Yue Liu, Xiao Peng, Shu-Yue Yan et al.· Earth's Future· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A growing trend involves integrating human knowledge into learning frameworks, leveraging subtle human feedback to refine AI models. While these approaches have shown promising results in practice, the theoretical understanding of when and why such approaches are effective remains limited. This work takes steps toward...
The Anchored Extra-Proximal (AEP) framework is introduced, which combines an anchored extrapolation step with an inexact anchored proximal update satisfying a relative-error condition to recover the composite Fast Extragradient method in the first-order setting.
Matrix completion, the problem of estimating missing entries in a matrix from noisily observed ones, underlies a diverse array of problems such as recommender systems and counterfactual outcome estimation in panel data. Many algorithms address the problem using regularized least squares, often with the nuclear norm as...
A central goal when designing treatment policies is often to"do no harm", that is, to avoid interventions that improve average outcomes while worsening outcomes for some individuals. A widely used notion for harm is the fraction of negatively affected (FNA), defined as the probability that an intervention decreases an...
Rui-Zi Yan, Dennis Frauen, Maresa Schröder et al.· 0 citations
We study the detection of LLM-generated text under editing and contamination. Modeling human and machine text as finite-order Markov processes with Huber contamination, we characterize an exact boundary for reliable detection under our assumptions. Detection is impossible when contamination is sufficiently large relati...
Worst-case Optimal Recovery (OR) and Bayesian learning describe the same Gaussian-quadratic-Hilbert problems in two vocabularies. We sharpen the correspondence - the radius of information equals a nugget-optimized GP posterior variance and is attained by the posterior mean at a closed-form balance nugget - and measure,...
A variational formulation inspired by empirical risk minimization subject to relative entropy regularization (ERM-RER) is proposed using a variational formulation inspired by empirical risk minimization subject to relative entropy regularization to guarantee exact unlearning for Gibbs supervised learning algorithms.
Yaiza Bermudez, S. Perlaza, Iñaki Esnaola· International Symposium on I...· 2 citations
Flow-Based Distribution Matching is introduced, a non-adversarial framework that learns this reference-directed geometry through spherical conditional velocity regression that achieves performance nearly on par with DM and remains competitive with existing SSL methods.
Yu-Ling Jiao, Wen-Sen Ma, Hou-Duo Qi et al.· 0 citations
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
