Under weak spherical symmetry and noisy data, SVD-based selection on the canonical dependence matrix yields asymptotically optimal error exponents up to a residual depending on symmetry deviation and noise levels.
Representation learning: A review and new perspectives
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Introduces integration, metastability, and dynamical stability index measures from layer activations and reports patterns distinguishing CIFAR-10 from CIFAR-100 difficulty plus early convergence signals across ResNet variants, DenseNet, MobileNetV2, VGG-16, and a Vision Transformer.
Reveals hidden human-like spans in machine-generated texts that raise detection complexity and proposes a stacked enhancement framework with hard-EM optimization to improve detectors across LLMs.
Randomly initialized networks trained solely via peer-to-peer self-distillation learn useful representations that outperform random baselines on downstream tasks.
citing papers explorer
-
Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
Under weak spherical symmetry and noisy data, SVD-based selection on the canonical dependence matrix yields asymptotically optimal error exponents up to a residual depending on symmetry deviation and noise levels.
-
Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach
Introduces integration, metastability, and dynamical stability index measures from layer activations and reports patterns distinguishing CIFAR-10 from CIFAR-100 difficulty plus early convergence signals across ResNet variants, DenseNet, MobileNetV2, VGG-16, and a Vision Transformer.
-
Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement
Reveals hidden human-like spans in machine-generated texts that raise detection complexity and proposes a stacked enhancement framework with hard-EM optimization to improve detectors across LLMs.
-
Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus
Randomly initialized networks trained solely via peer-to-peer self-distillation learn useful representations that outperform random baselines on downstream tasks.