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

10 results for “VICReg”

VNIbCReg: VICReg with Neighboring-Invariance and better-Covariance Evaluated on Non-stationary Seismic Signal Time Seriescs.LG

Study combines VICReg and TNC for better encoding of non-stationary seismic signals.

problem Ineffective self-supervised learning on non-stationary time series.

method Combines VICReg and Temporal Neighborhood Coding (TNC).

result Effective for self-supervised learning on non-stationary seismic signals.

self-supervised learning non-stationary time series VICReg TNC seismic signal

2022-04-06abs ↗pdf ↗

Kernel VICReg for Self-Supervised Learning in Reproducing Kernel Hilbert Spacestat.ML

Kernel VICReg improves SSL in RKHS, capturing nonlinear structures.

problem Limited ability of existing SSL methods to handle nonlinear dependencies.

method Kernel VICReg framework in RKHS, kernelizing VICReg objectives.

result Kernel VICReg mitigates representational collapse and improves performance.

self-supervised learning reproducing kernel hilbert space kernel methods representation learning nonlinear structures

2025-09-08abs ↗pdf ↗

GraphVICRegHSIC: Towards improved self-supervised representation learning for graphs with a hyrbid loss functioncs.LG

Paper proposes a hybrid loss function for graph self-supervised learning.

problem Improving self-supervised representation learning for graphs.

method Hybrid loss function combining VICReg and HSIC.

result Hybrid loss function outperformed other methods in 4 out of 7 cases.

graph neural networks self-supervised learning hybrid loss function VICReg HSIC

2021-05-25abs ↗pdf ↗

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methodscs.LG

Unified framework for SSL methods linking contrastive and non-contrastive approaches.

problem Lack of theoretical foundations and design guidelines for SSL methods.

method Spectral manifold learning framework to unify SSL methods.

result Theoretical bridge between contrastive and non-contrastive methods.

Self-Supervised Learning Spectral Manifold Learning VICReg SimCLR BarlowTwins

2022-05-23abs ↗pdf ↗

Computer Vision Self-supervised Learning Methods on Time Seriescs.LG

Computer vision SSL methods show effectiveness on time series data.

problem Evaluate if computer vision SSL frameworks are effective on time series data.

method Evaluated on UCR and UEA archives, proposed a new method improving VICReg.

result Computer vision SSL frameworks can be effective on time series data.

self-supervised learning computer vision time series covariance iterative normalization

2021-09-02abs ↗pdf ↗

Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximationcs.LG

Unified framework interprets SSL models, revealing biases.

problem Interpreting black-box SSL models for transparency.

method KREPES framework using Representer Landmarks and Nyström approximation.

result Direct audit of SSL latent space without supervision.

self-supervised learning interpretable models representer theorem nyström approximation bias detection

2025-09-29abs ↗pdf ↗

SinSim: Sinkhorn-Regularized SimCLRcs.LG

SinSim improves self-supervised learning by integrating optimal transport into contrastive learning.

problem Lack of explicit regularization in contrastive learning methods leads to suboptimal generalization.

method Integrates Sinkhorn regularization from optimal transport theory into SimCLR.

result SinSim outperforms SimCLR and other self-supervised methods on various datasets.

self-supervised learning contrastive learning optimal transport sinkhorn regularization representation learning

2025-02-13abs ↗pdf ↗

Minimalistic Unsupervised Learning with the Sparse Manifold Transformcs.LG

Minimalistic unsupervised learning with sparse manifold transform achieves SOTA performance.

problem Achieving state-of-the-art unsupervised learning performance without complex engineering.

method Sparse manifold transform, leveraging sparse coding, manifold learning, and slow feature analysis.

result 99.3% KNN top-1 accuracy on MNIST, 81.1% on CIFAR-10, and 53.2% on CIFAR-100.

unsupervised learning sparse coding manifold learning slow feature analysis state-of-the-art

2022-09-30abs ↗pdf ↗

Self-Supervised Learning by Curvature Alignmentcs.LG

CurvSSL improves SSL by aligning local manifold curvature.

problem Improving self-supervised learning by capturing local manifold geometry.

method CurvSSL augments Barlow Twins with a curvature-based regularizer to align and decorrelate embeddings across augmentations.

result Curvature-regularized SSL yields competitive or improved linear evaluation performance.

self-supervised learning curvature regularization Barlow Twins local manifold geometry MNIST

2025-11-21abs ↗pdf ↗

Metric-Aware Principal Component Analysis (MAPCA):A Unified Framework for Scale-Invariant Representation Learningcs.LG

Unified framework for scale-invariant representation learning using MAPCA.

problem Learning invariant representations in data.

method Metric-Aware Principal Component Analysis (MAPCA) based on generalized eigenproblem.

result MAPCA provides a unified geometric language for various self-supervised learning objectives.

Principal Component Analysis Scale Invariance Self-Supervised Learning Metric Matrix Invariant PCA

2026-04-15abs ↗pdf ↗