The paper introduces SACReg, a spectral anti-collapse regularizer that enforces λ-balance across weight matrices to prevent dimensional collapse in the backbone of joint-embedding self-supervised learning models. Applied to JEPA, the resulting λ-JEPA improves ImageNet-1k classification and linear-probe transfer on eight image datasets, and also outperforms prior video self-supervised methods on Something-Something-v2 and Kinetics-400.
By Berker Demirel, Cl\'ementine Domin\'e, Valentino Maiorca, Marco Fumero, Marco Mondelli, Francesco Locatello
The paper investigates self‑supervised pre‑training that uses multiple data augmentations of the same unlabeled sample. It shows that pooling these dependent augmentations together yields statistical estimation error bounds that are never worse than, and sometimes better than, partitioning the data into independent subsets. The analysis explains why using many augmentations is practically advantageous, especially when their correlations have mild effects or reduce estimation variance.
By Maximilian Fleissner, Debarghya Ghoshdastidar, Samory Kpotufe
arXiv:2205. 07739v4 Announce Type: replace-cross Abstract: Self-training (ST) is a simple yet effective semi-supervised learning method.
By Takashi Takahashi
arXiv:2609.15825v1 Announce Type: new
Abstract: A self-supervised encoder is trained once, frozen, and reused through lightweight probes on tasks nobody named at training time; the practitioner's que...
By Dier Tang, Jing Yee Tan, Guangyue Han
arXiv:2609.14451v1 Announce Type: cross
Abstract: Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the ps...
By Itai David, Daphna Weinshall
arXiv:2607. 22931v1 Announce Type: new Abstract: Analytic Continual Learning (ACL) offers a computationally efficient alternative to gradient-based approaches.
By Quyen Tran, Hai Nguyen, Quan Dao, Zhuowei Li, Nam Le, Trung Le, Dimitris Metaxas
The paper extends the study of relatively smart learning, showing that ERM and any proper consistent learner are relatively smart for binary classification in the distribution‑free setting, achieving a quadratic sample‑complexity blowup. It further demonstrates that semi‑supervised relatively smart learning is possible with only a quadratic blowup in unlabeled data and no blowup in labeled data, though this requires a leave‑most‑out transductive approach and incurs intractability when only an agnostic ERM oracle is available. The results clarify the trade‑offs between sample efficiency, label efficiency, and computational tractability in relatively smart learning.
By Shaddin Dughmi, Alireza F. Pour
The paper introduces Spectral Transductive Refinement (STR), a training‑free method that refines class prototypes at test time using the geometry of a joint k‑nearest‑neighbour graph and a normalized‑Laplacian spectral coordinate system. STR operates solely on frozen visual embeddings, iteratively updating pseudo‑labelled queries to improve one‑shot and few‑shot classification under domain shift. Experiments on ResNet‑18 and ResNet‑10 backbones show STR outperforms single‑prototype baselines and rivals meta‑trained cross‑domain few‑shot methods, achieving the best 1‑shot average across eight target domains.
By Fahim Rahman, S. M. Tanjeeb Meheran Rohan, Md. Taimum Ibne Sayed, Asaduzzaman Herok, Md. Bakhtiar Hasan
The paper investigates minimal‑norm interpolation and λ2‑regularized logistic‑loss minimization for binary classification using univariate two‑layer ReLU networks. It provides exact geometric characterizations of optimal classifiers, showing that unpenalized hidden‑layer biases yield continuous piecewise‑affine functions that tightly follow label switches, while penalized biases produce a unique, sparsest classifier with a single kink per same‑label segment. Adding a free affine skip connection does not change these function‑space solutions but guarantees that every KKT point becomes globally optimal, eliminating suboptimal KKT points that can arise without the skip connection.
By Karolina Drabik, Ben Lewis, Antoni Puch, Etienne Boursier, Piotr Hofman, Matthias Englert, Ranko Lazi\'c
arXiv:2606. 19411v1 Announce Type: new Abstract: Selecting a small, diverse, high-quality subset from a massive pool of candidates is a recurring primitive in modern machine learning -- data curation and coreset selection for training and fine-tuning large models, active-learning batch acquisition, prompt and exemplar selection for in-context learning, retrieval diversification, and experimental design.
By Richard Yi Da Xu
arXiv:2511. 22823v2 Announce Type: replace-cross Abstract: Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire.
By Miao Zhang, Junpeng Li, Changchun Hua, Yana Yang
JEPAMatch introduces a new semi‑supervised learning framework that replaces traditional output‑thresholding with explicit geometric shaping of latent representations. By combining the FlexMatch loss with a latent‑space regularization inspired by LeJEPA, the method encourages isotropic Gaussian structure in the embedding space, mitigating class imbalance and noisy pseudo‑labels. Experiments on CIFAR‑100, STL‑10, and Tiny‑ImageNet show consistent performance gains and faster convergence compared to existing FixMatch‑based baselines.
By Ali Aghababaei-Harandi, Aude Sportisse, Massih-Reza Amini