On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “VNNs”

Sparse Covariance Neural Networkscs.LG

S-VNNs improve VNNs by sparsifying covariance matrices.

problem Spurious correlations in covariance matrices degrade VNNs' performance and efficiency.

method Apply sparsification techniques on sample covariance matrix and integrate into VNN architecture.

result S-VNNs achieve improved performance, stability, and reduced computational time.

covariance neural networks sparsity sparse covariance sparsification neuroscience

2024-10-02abs ↗pdf ↗

Transferability of coVariance Neural Networks and Application to Interpretable Brain Age Prediction using Anatomical Featurescs.LG

VNNs transfer well across datasets for brain age prediction using cortical thickness features.

problem Predicting brain age using anatomical features.

method Transferability of coVariance neural networks (VNNs) in brain age prediction.

result VNNs can assign anatomical interpretability to elevated brain age gap in AD.

brain age prediction cortical thickness transferability VNNs covariance matrices

2023-05-02abs ↗pdf ↗

coVariance Neural Networkscs.LG

A new GNN architecture called coVariance neural network (VNN) improves stability and transferability of covariance matrix analysis.

problem Stability and transferability issues in covariance matrix analysis.

method Developed coVariance neural network (VNN) that operates on sample covariance matrices.

result VNN is more stable and transferable than PCA-based approaches.

covariance matrix graph neural networks stability transferability principal component analysis

2022-05-31abs ↗pdf ↗

General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcs.LG

Generalizes neural network verification by adding arbitrary cutting planes.

problem Handling general cutting plane constraints in neural network verification.

method Generalized bound propagation method (GCP-CROWN) that allows arbitrary cutting plane constraints.

result GCP-CROWN significantly improves neural network verification performance.

neural network verification bound propagation cutting planes mixed integer programming GPU acceleration

2022-08-11abs ↗pdf ↗

Deep Active Learning via Open Set Recognitioncs.LG

Active learning selects most informative unlabeled samples for labeling.

problem Efficiently label unlabeled data in applications with scarce labeled data.

method Formulated as open-set recognition, uses VNNs to identify uncertain samples.

result Achieved state-of-the-art results on MNIST, CIFAR-10, and CIFAR-100.

active learning open set recognition variational neural networks uncertainty sampling oracle labeling

2020-07-04abs ↗pdf ↗

Covariance Scattering Transformscs.LG

CSTs improve stability in covariance spectrum analysis without training.

problem Stability and expressiveness in covariance spectrum analysis.

method Sequential application of covariance wavelet filters to input data.

result Stable and expressive hierarchical representations in low-data settings.

covariance spectrum stability wavelets neural networks machine learning

2025-11-12abs ↗pdf ↗

BaB-prob: Branch and Bound with Preactivation Splitting for Probabilistic Verification of Neural Networkscs.LG

Extends branch and bound for probabilistic neural network verification.

problem Probabilistic verification of neural networks.

method Split preactivations, use linear bounds, divide problems iteratively.

result Sound and complete for feedforward-ReLU networks.

neural networks probabilistic verification branch and bound preactivation splitting linear bounds

2025-09-30abs ↗pdf ↗

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcs.LG

Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.

problem Handling neuron split constraints in incomplete neural network verification.

method β-CROWN, which optimizes parameters β to encode neuron splits and uses them in bound propagation.

result β-CROWN significantly speeds up verification while maintaining high accuracy.

neural network verification bound propagation neuron splits complete verification incomplete verification

2021-03-11abs ↗pdf ↗