The paper introduces GRIDS, a framework using Local Intrinsic Dimensionality (LID) to detect anomalies in self-supervised speech model representations, showing that LID elevation correlates with ASR d…

This paper compares PCA and LPC for dimensionality reduction in cyberattack classification, demonstrating that both techniques can achieve substantial feature compression with minimal loss of classifi…

The authors show that an explicit information bottleneck in a recurrent neural network is necessary for rotational and out-of-distribution generalization in a time-series prediction task, and that the…

This paper simplifies the proof of the bound on the target dimension for reducing the dimension of high-dimensional polygonal curves using random projections, extending it to various distance measures…

This paper introduces a new way to represent finite posets as subwords of finite words in categories, and characterizes the monic categories that admit this representation.

The authors propose a framework for enhancing the believability of large language models in one-to-one conversation by focusing on dimensional completeness and expressing first-person stances in the a…

This paper explores the use of standard graph algorithms on UMAP's internal k-nearest-neighbor graph to enhance data analysis.

The paper introduces a computational framework using Hodge zero-modes to track the geometry of topological features in parameter-dependent data, providing metrics like curvature and holonomy to quanti…

The paper proposes using geometric metrics, specifically eigenspace alignment, to monitor the structural integrity of large behavioral populations, demonstrating its effectiveness in detecting network…

This paper investigates the correlation between dimensions of self-supervised speech features and speech characteristics, finding that content dimensions primarily capture intensity, formants, and voi…

This paper identifies scattering network architectures that maximize separation capacity for data with low intrinsic dimension by characterizing and bounding the separation capacity of general feature…