Imagen de Portada

A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Feigin, Shlomo Libo, Fleissner, Maximilian, Ghoshdastidar, Debarghya
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization
por: Esser, Pascal, et al.
Publicado: (2025)

Infinite Width Limits of Self Supervised Neural Networks
por: Fleissner, Maximilian, et al.
Publicado: (2024)

A Probabilistic Model for Non-Contrastive Learning
por: Fleissner, Maximilian, et al.
Publicado: (2025)

Explainable Clustering Beyond Worst-Case Guarantees
por: Fleissner, Maximilian, et al.
Publicado: (2024)

Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders
por: Ham, Jonghyun, et al.
Publicado: (2025)

Explaining Kernel Clustering via Decision Trees
por: Fleissner, Maximilian, et al.
Publicado: (2024)

Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
por: Zarvandi, Maedeh, et al.
Publicado: (2025)

Transformers Provably Learn Sparse XOR with Polylogarithmic Parameters
por: Han, Yaomengxi, et al.
Publicado: (2025)

On the Convergence of Gradient Descent for Large Learning Rates
por: Crăciun, Alexandru, et al.
Publicado: (2024)

Tight PAC-Bayesian Risk Certificates for Contrastive Learning
por: Van Elst, Anna, et al.
Publicado: (2024)

Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations
por: Crăciun, Alexandru, et al.
Publicado: (2025)

Gaussian Process Limit Reveals Structural Benefits of Graph Transformers
por: Ayday, Nil, et al.
Publicado: (2026)

Exact Generalisation Error Exposes Benchmarks Skew Graph Neural Networks Success (or Failure)
por: Ayday, Nil, et al.
Publicado: (2025)

Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit
por: Eppert, Martin, et al.
Publicado: (2025)

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
por: Gosch, Lukas, et al.
Publicado: (2024)

When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?
por: Anil, Gautham Govind, et al.
Publicado: (2024)

Nonparametric Kernel Clustering with Bandit Feedback
por: Thuot, Victor, et al.
Publicado: (2026)

Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections
por: Singh, Anurag, et al.
Publicado: (2023)

Exact Certification of (Graph) Neural Networks Against Label Poisoning
por: Sabanayagam, Mahalakshmi, et al.
Publicado: (2024)

Robustness Certificates for Neural Networks against Adversarial Attacks
por: Taheri, Sara, et al.
Publicado: (2025)

Generalization Certificates for Adversarially Robust Bayesian Linear Regression
por: Sabanayagam, Mahalakshmi, et al.
Publicado: (2025)

Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks
por: Ayday, Nil, et al.
Publicado: (2026)

Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
por: Mohgaonkar, Ajinkya, et al.
Publicado: (2026)

T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data
por: Thimonier, Hugo, et al.
Publicado: (2024)

Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models
por: Lecoiu, Radu, et al.
Publicado: (2026)

DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
por: Hu, Jiaming, et al.
Publicado: (2025)

An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
por: Cui, Jingyi, et al.
Publicado: (2025)

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
por: Huang, Yu, et al.
Publicado: (2024)

Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
por: Duan, Chenguang, et al.
Publicado: (2024)

UTOPIA: Universally Trainable Optimal Prediction Intervals Aggregation
por: Fan, Jianqing, et al.
Publicado: (2023)

Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
por: Ge, Jiawei, et al.
Publicado: (2024)

Deep Augmentation: Dropout as Augmentation for Self-Supervised Learning
por: Brüel-Gabrielsson, Rickard, et al.
Publicado: (2023)

Learning to Retrieve for Environmental Knowledge Discovery: An Augmentation-Adaptive Self-Supervised Learning Framework
por: Luo, Shiyuan, et al.
Publicado: (2025)

Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality
por: Chen, Hanxiao, et al.
Publicado: (2026)

Weak Augmentation Guided Relational Self-Supervised Learning
por: Zheng, Mingkai, et al.
Publicado: (2022)

Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
por: Eastwood, Cian, et al.
Publicado: (2023)

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
por: Zhai, Runtian, et al.
Publicado: (2023)

Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning
por: Jian, Xiangru, et al.
Publicado: (2024)

You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
por: Moutakanni, Théo, et al.
Publicado: (2024)

IBMA: An Imputation-Based Mixup Augmentation Using Self-Supervised Learning for Time Series Data
por: Nguyen, Dang Nha, et al.
Publicado: (2025)