Copertina

Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Esser, Pascal, Fleissner, Maximilian, Ghoshdastidar, Debarghya
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning
di: Feigin, Shlomo Libo, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Cluster Specific Representation Learning
di: Sabanayagam, Mahalakshmi, et al.
Pubblicazione: (2024)

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

Collaborative Unlabeled Data Optimization
di: Shang, Xinyi, et al.
Pubblicazione: (2025)

Learning from Uncertain Similarity and Unlabeled Data
di: Wei, Meng, et al.
Pubblicazione: (2025)

Offline Reinforcement Learning with Domain-Unlabeled Data
di: Nishimori, Soichiro, et al.
Pubblicazione: (2024)

On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
di: Yu, Bing, et al.
Pubblicazione: (2020)

High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling
di: Yin, Yuxuan, et al.
Pubblicazione: (2023)

Understanding Contrastive Representation Learning from Positive Unlabeled (PU) Data
di: Acharya, Anish, et al.
Pubblicazione: (2024)

Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
di: Zhao, Hengwei, et al.
Pubblicazione: (2025)

Contributions to the Decision Theoretic Foundations of Machine Learning and Robust Statistics under Weakly Structured Information
di: Jansen, Christoph
Pubblicazione: (2025)

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
di: Takahashi, Hiroshi, et al.
Pubblicazione: (2024)

Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
di: Liu, Renpu, et al.
Pubblicazione: (2026)

Making Better Use of Unlabelled Data in Bayesian Active Learning
di: Smith, Freddie Bickford, et al.
Pubblicazione: (2024)

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

Proper Learnability and the Role of Unlabeled Data
di: Asilis, Julian, et al.
Pubblicazione: (2025)

Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learning
di: Malomgré, Elias, et al.
Pubblicazione: (2025)

LAUD: Integrating Large Language Models with Active Learning for Unlabeled Data
di: Chou, Tzu-Hsuan, et al.
Pubblicazione: (2025)

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