4 papers · 1 filter
Gauge-invariant representation holonomy
Vasileios Sevetlidis, George Pavlidis
Deep networks learn internal representations whose geometry--how features bend, rotate, and evolve--affects both generalization and robustness. Existing similarity measures such as…
Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps
Vasileios Sevetlidis, George Pavlidis
Modern deep-learning training is not memoryless. Updates depend on optimizer moments and averaging, data-order policies (random reshuffling vs with-replacement, staged augmentation…
Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability
Vasileios Sevetlidis, George Pavlidis
This work proposes neural training as a \emph{process tensor}: a multi-time map that takes a sequence of controllable instruments (batch choices, augmentations, optimizer micro-ste…
Angular Regularization for Positive-Unlabeled Learning on the Hypersphere
Vasileios Sevetlidis, George Pavlidis, Antonios Gasteratos
Positive-Unlabeled (PU) learning addresses classification problems where only a subset of positive examples is labeled and the remaining data is unlabeled, making explicit negative…