March 2026

arXiv:2507.21783v2 Announce Type: replace-cross Abstract: The performance of predictive models in clinical settings often degrades when deployed in new hospitals due to distribution shifts. This paper presents a large-scale study of causality-inspired domain generalization on heterogeneous multi-center intensive care unit (ICU) data. We apply anchor regression and introduce anchor boosting, a novel, tree-based nonlinear extension, to a large dataset comprising 400,000 patients from nine distinct ICU databases. We find that anchor regularization yields improvements of out-of-distribution performance, particularly […]

Ver mais

arXiv:2506.16965v3 Announce Type: replace-cross Abstract: Ensemble learning remains a cornerstone of machine learning, with stacking used to integrate predictions from multiple base learners through a meta-model. However, deep stacking remains uncommon due to feature redundancy, complexity, and computational burden. To address these limitations, RocketStack is introduced as a level-aware recursive stacking architecture explored up to ten stacking levels, extending beyond prior architectures. At level 1, base-learner predictions are fused with original features; at later levels, weaker learners are […]

Ver mais

arXiv:2505.16953v3 Announce Type: replace-cross Abstract: Multimodal learning is of continued interest in artificial intelligence-based applications, motivated by the potential information gain from combining different data modalities. However, modalities observed in the source environment may differ from the modalities observed in the target environment due to multiple factors, including cost, hardware failure, or the perceived textit{informativeness} of a given modality. This change in missingness patterns between the source and target environment has not been carefully studied. Na{“i}ve estimation of […]

Ver mais

arXiv:2505.14042v3 Announce Type: replace-cross Abstract: Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical analysis suggesting that adversarially pretrained transformers can serve as universally robust foundation models — models that can adapt robustly to diverse downstream tasks with only lightweight tuning. Specifically, we demonstrate that single-layer linear transformers, after adversarial pretraining across a variety of classification tasks, can generalize robustly […]

Ver mais

arXiv:2505.12096v4 Announce Type: replace-cross Abstract: The statistical properties of deep neural networks (DNNs) at initialization play an important role to comprehend their trainability and the intrinsic architectural biases they possess before data exposure Well established mean field (MF) theories have uncovered that the distribution of parameters of randomly initialized networks strongly influences the behavior of the gradients, dictating whether they explode or vanish. Recent work has showed that untrained DNNs also manifest an initial guessing bias (IGB), in […]

Ver mais

arXiv:2504.08428v2 Announce Type: replace-cross Abstract: A fundamental problem in statistics is measuring the correlation between two rankings of a set of items. Kendall’s $tau$ and Spearman’s $rho$ are well established correlation coefficients whose symmetric structure guarantees zero expected value between two rankings randomly chosen with uniform probability. In many modern applications, however, greater importance is assigned to top-ranked items, motivating weighted variants of these coefficients. Such weighting schemes generally break the symmetry of the original formulations, resulting in […]

Ver mais

arXiv:2502.21278v2 Announce Type: replace-cross Abstract: There is strong empirical evidence that the state-of-the-art diffusion modeling paradigm leads to models that memorize the training set, especially when the training set is small. Prior methods to mitigate the memorization problem often lead to a decrease in image quality. Is it possible to obtain strong and creative generative models, i.e., models that achieve high generation quality and low memorization? Despite the current pessimistic landscape of results, we make significant progress in […]

Ver mais

arXiv:2410.23450v2 Announce Type: replace-cross Abstract: We study offline off-dynamics reinforcement learning (RL) to utilize data from an easily accessible source domain to enhance policy learning in a target domain with limited data. Our approach centers on return-conditioned supervised learning (RCSL), particularly focusing on Decision Transformer (DT) type frameworks, which can predict actions conditioned on desired return guidance and complete trajectory history. Previous works address the dynamics shift problem by augmenting the reward in the trajectory from the source […]

Ver mais

arXiv:2410.08939v2 Announce Type: replace-cross Abstract: We design and analyze unbiased Markov chain Monte Carlo (MCMC) schemes based on couplings of blocked Gibbs samplers (BGSs), whose total computational costs scale linearly with the number of parameters and data points. Our methodology is designed for and applicable to high-dimensional BGS with conditionally independent blocks, which are often encountered in Bayesian modeling. We provide bounds on the expected number of iterations needed for coalescence for Gaussian targets, as well as on […]

Ver mais

arXiv:2407.08086v2 Announce Type: replace-cross Abstract: Kernels are a fundamental technical primitive in machine learning. In recent years, kernel-based methods such as Gaussian processes are becoming increasingly important in applications where quantifying uncertainty is of key interest. In settings that involve structured data defined on graphs, meshes, manifolds, or other related spaces, defining kernels with good uncertainty-quantification behavior, and computing their value numerically, is less straightforward than in the Euclidean setting. To address this difficulty, we present GeometricKernels, a […]

Ver mais