arXiv:2510.00504v1 Announce Type: new Abstract: When training large-scale models, the performance typically scales with the number of parameters and the dataset size according to a slow power law. A fundamental theoretical and practical question is whether comparable performance can be…
arXiv:2510.00463v1 Announce Type: new Abstract: This paper studies the adversarial robustness of conformal novelty detection. In particular, we focus on AdaDetect, a powerful learning-based framework for novelty detection with finite-sample false discovery rate (FDR) control. While AdaDetect provides rigorous statistical…
arXiv:2510.00367v1 Announce Type: new Abstract: Neural network-based methods for (un)conditional density estimation have recently gained substantial attention, as various neural density estimators have outperformed classical approaches in real-data experiments. Despite these empirical successes, implementation can be challenging due to the…
arXiv:2410.02025v2 Announce Type: replace-cross Abstract: In this work, we explore the theoretical properties of conditional deep generative models under the statistical framework of distribution regression where the response variable lies in a high-dimensional ambient space but concentrates around a potentially…
arXiv:2510.01098v1 Announce Type: new Abstract: We study in-context learning (ICL) of linear regression in a deep linear self-attention model, characterizing how performance depends on various computational and statistical resources (width, depth, number of training steps, batch size and data per…
arXiv:2410.09836v2 Announce Type: replace-cross Abstract: Time series forecasting, which aims to predict future values based on historical data, has garnered significant attention due to its broad range of applications. However, real-world time series often exhibit complex non-uniform distribution with varying…
arXiv:2510.00048v1 Announce Type: cross Abstract: Early and accurate diagnosis of Alzheimer Disease is critical for effective clinical intervention, particularly in distinguishing it from Mild Cognitive Impairment, a prodromal stage marked by subtle structural changes. In this study, we propose a…
arXiv:2505.15626v2 Announce Type: replace-cross Abstract: Concept-based explanation methods aim at making machine learning models more transparent by finding the most important semantic features of an input (e.g., colors, patterns, shapes) for a given prediction task. However, these methods generally ignore…
arXiv:2510.00079v1 Announce Type: cross Abstract: We introduce textbf{Directed Information $gamma$-covering}, a simple but general framework for redundancy-aware context engineering. Directed information (DI), a causal analogue of mutual information, measures asymmetric predictiveness between chunks. If $operatorname{DI}_{i to j} ge H(C_j) –…
arXiv:2506.24007v3 Announce Type: replace-cross Abstract: This study investigates minimax and Bayes optimal strategies in fixed-budget best-arm identification. We consider an adaptive procedure consisting of a sampling phase followed by a recommendation phase, and we design an adaptive experiment within this…
