arXiv:2405.18499v3 Announce Type: replace Abstract: Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…
arXiv:2509.15591v1 Announce Type: cross Abstract: Generative modeling, representation learning, and classification are three core problems in machine learning (ML), yet their state-of-the-art (SoTA) solutions remain largely disjoint. In this paper, we ask: Can a unified principle address all three? Such…
arXiv:2506.02260v3 Announce Type: replace Abstract: Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack of gold-standard labels and incomplete sensor data. While self-supervised learning approaches have shown promise…
arXiv:2509.15594v1 Announce Type: cross Abstract: We study the estimation of distributional treatment effects in randomized experiments with imperfect compliance. When participants do not adhere to their assigned treatments, we leverage treatment assignment as an instrumental variable to identify the local…
arXiv:2306.16571v2 Announce Type: replace-cross Abstract: While recurrent event analyses have been extensively studied, limited attention has been given to causal inference within the framework of recurrent event analysis. We develop a multiply robust estimation framework for causal inference in recurrent…
arXiv:2509.15641v1 Announce Type: cross Abstract: We highlight a fundamental connection between information geometry and variational Bayes (VB) and discuss its consequences for machine learning. Under certain conditions, a VB solution always requires estimation or computation of natural gradients. We show…
arXiv:2410.05837v3 Announce Type: replace-cross Abstract: The Langevin algorithm is a classic method for sampling from a given pdf in a real space. In its basic version, it only requires knowledge of the gradient of the log-density, also called the score…
arXiv:2509.15776v1 Announce Type: cross Abstract: The Lookahead optimizer enhances deep learning models by employing a dual-weight update mechanism, which has been shown to improve the performance of underlying optimizers such as SGD. However, most theoretical studies focus on its convergence…
arXiv:2410.22069v3 Announce Type: replace-cross Abstract: We study the implicit bias of the general family of steepest descent algorithms with infinitesimal learning rate in deep homogeneous neural networks. We show that: (a) an algorithm-dependent geometric margin starts increasing once the networks…
arXiv:2509.15797v1 Announce Type: cross Abstract: Latent space model plays a crucial role in network analysis, and accurate estimation of latent variables is essential for downstream tasks such as link prediction. However, the large number of parameters to be estimated presents…
