arXiv:2407. 12288v5 Announce Type: replace-cross Abstract: The progress of machine learning over the past decade is undeniable.
arXiv:2507. 08922v3 Announce Type: replace-cross Abstract: Continual learning is an online paradigm where a learner continually accumulates knowledge from different tasks encountered over sequential time steps.
arXiv:2511. 04666v4 Announce Type: replace Abstract: A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data.
arXiv:2512. 21315v2 Announce Type: replace Abstract: The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the observations.
arXiv:2603. 14894v3 Announce Type: replace-cross Abstract: Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations.
The paper introduces the concept of Wide Learning, which examines how a learner’s internal state can expand its ability to generate informative evidence under fixed resources and primitive affordances. By formalizing effective epistemic reach—defined by learner state, deployment budget, reliability threshold, and evaluation distribution—the authors demonstrate, through a controlled construction, that learning can significantly alter the probability of successfully realizing a diagnostic that was previously unlikely. The study shows that even with identical observable laws, a calibrated learner can achieve perfect diagnostic realization, highlighting the impact of learning on the scope of attainable evidence.
arXiv:2607. 22961v1 Announce Type: new Abstract: Verbalized Machine Learning (VML) parameterizes a model as a natural-language prompt that an LLM evaluates as f(x; theta).
arXiv:2604. 04535v2 Announce Type: replace Abstract: Modern machine learning systems, such as generative models and recommendation systems, often evolve through a cycle of deployment, user interaction, and periodic model updates.
arXiv:2608. 09074v1 Announce Type: cross Abstract: We develop a new approach to Personalized Federated Learning across heterogeneous clients using Nonparametric Empirical Bayes (NPEB).
arXiv:2606. 23838v1 Announce Type: new Abstract: When two or more parameters or labels produce similar data, they are degenerate, or hard to distinguish.
Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the problem of automated data selection, or "intrinsic curiosity", remains a significant challenge.
The paper introduces a PAC‑Bayesian, algorithm‑agnostic framework to quantify the value of privileged information (PI) in Learning Using Privileged Information (LUPI). By comparing the tightest achievable risk bounds with and without PI, the authors derive a training‑time metric that estimates the maximum potential gain from PI without requiring test data. Experiments in supervised and unsupervised settings show a strong correspondence between this metric and actual test‑time performance improvements.
arXiv:2604. 13130v2 Announce Type: replace Abstract: We study learning to learn through the lens of hyperparameter tuning.