arXiv:2606. 11130v1 Announce Type: new Abstract: We study the task of agnostically learning general (as opposed to homogeneous) ReLUs under the Gaussian distribution with respect to the squared loss.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
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.
The paper investigates how the ability to synthesize arbitrary queries (membership queries) changes the sample complexity of active learning compared to the traditional pool-based setting. It shows that some hypothesis classes that only achieve polynomial error decay with pool-based queries become exponentially learnable when synthesis is allowed, revealing a significant gap in learning difficulty. The authors propose sufficient conditions, provide examples, and suggest a conjectural framework to identify classes that benefit from synthesized queries.
arXiv:2608. 25326v1 Announce Type: new Abstract: In transductive classification, an adversary fixes a labeled population, one label is hidden uniformly, and the learner sees all remaining labels.
arXiv:2310. 10092v4 Announce Type: replace Abstract: This paper explores the use of linear aggregation to protect the privacy of sensitive training labels through the concept of \emph{label differential privacy} (label-DP) while maintaining regression task utility.
arXiv:2512.12870v2 Announce Type: replace-cross Abstract: Active Learning (AL) is commonly used in applications where labeling data is expensive or time-consuming. In practice, however, labels are of...
arXiv:2608. 07139v1 Announce Type: new Abstract: Uncertainty quantification is essential when deploying machine learning models in safety-critical applications.