arXiv:2506.00330v2 Announce Type: replace-cross Abstract: Mutual information (MI) is a fundamental measure of statistical dependence between two variables, yet accurate estimation from finite data remains notoriously difficult. No estimator is universally reliable, and common approaches fail in the high-dimensional, undersampled…
arXiv:2505.12171v2 Announce Type: replace-cross Abstract: State-space models (SSMs) are a class of networks for sequence learning that benefit from fixed state size and linear complexity with respect to sequence length, contrasting the quadratic scaling of typical attention mechanisms. Inspired from…
arXiv:2510.00076v1 Announce Type: new Abstract: We consider online and PAC learning of Littlestone classes subject to the constraint of approximate differential privacy. Our main result is a private learner to online-learn a Littlestone class with a mistake bound of $tilde{O}(d^{9.5}cdot…
arXiv:2508.03245v2 Announce Type: replace-cross Abstract: The increasing demand for data privacy has made machine unlearning (MU) essential for removing the influence of specific training samples from machine learning models while preserving performance on retained data. However, most existing MU methods…
arXiv:2510.01175v1 Announce Type: cross Abstract: While normalization techniques are widely used in deep learning, their theoretical understanding remains relatively limited. In this work, we establish the benefits of (generalized) weight normalization (WN) applied to the overparameterized matrix sensing problem. We…
arXiv:2510.01163v1 Announce Type: cross Abstract: The emergence of in-context learning (ICL) in large language models (LLMs) remains poorly understood despite its consistent effectiveness, enabling models to adapt to new tasks from only a handful of examples. To clarify and improve…
arXiv:2303.15121v4 Announce Type: replace-cross Abstract: We consider the problem of finite-time identification of linear dynamical systems from $T$ samples of a single trajectory. Recent results have predominantly focused on the setup where either no structural assumption is made on the…
arXiv:2510.00625v1 Announce Type: new Abstract: Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issues. To address this issue, model editing has emerged as a promising…
arXiv:2510.00743v1 Announce Type: cross Abstract: Assessing the perceptual quality of synthetic speech is crucial for guiding the development and refinement of speech generation models. However, it has traditionally relied on human subjective ratings such as the Mean Opinion Score (MOS),…
arXiv:2510.00620v1 Announce Type: new Abstract: While there has been a surge of interest in automated scientific discovery (ASD), especially with the emergence of LLMs, it remains challenging for tools to generate hypotheses that are both testable and grounded in the…
