Category Research Papers

Memory of recurrent networks: Do we compute it right? Giovanni Ballarin, Lyudmila Grigoryeva, Juan-Pablo Ortega; 25(243):1−38, 2024. Abstract Numerical evaluations of the memory capacity (MC) of recurrent neural networks reported in the literature often contradict well-established theoretical bounds. In this…

Tensor-train methods for sequential state and parameter learning in state-space models Yiran Zhao, Tiangang Cui; 25(244):1−51, 2024. Abstract We consider sequential state and parameter learning in state-space models with intractable state transition and observation processes. By exploiting low-rank tensor train…

FineMorphs: Affine-Diffeomorphic Sequences for Regression Michele Lohr, Laurent Younes; 25(245):1−38, 2024. Abstract A multivariate regression model of affine and diffeomorphic transformation sequences—FineMorphs—is presented. Leveraging concepts from shape analysis, model states are optimally “reshaped” by diffeomorphisms generated by smooth vector fields…

Fairness in Survival Analysis with Distributionally Robust Optimization Shu Hu, George H. Chen; 25(246):1−85, 2024. Abstract We propose a general approach for encouraging fairness in survival analysis models that is based on minimizing a worst-case error across all subpopulations that…

Label Alignment Regularization for Distribution Shift Ehsan Imani, Guojun Zhang, Runjia Li, Jun Luo, Pascal Poupart, Philip H.S. Torr, Yangchen Pan; 25(247):1−32, 2024. Abstract Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of…

PromptBench: A Unified Library for Evaluation of Large Language Models Kaijie Zhu, Qinlin Zhao, Hao Chen, Jindong Wang, Xing Xie; 25(254):1−22, 2024. Abstract The evaluation of large language models (LLMs) is crucial to assess their performance and mitigate potential security…

Gaussian Interpolation Flows Yuan Gao, Jian Huang, and Yuling Jiao; 25(253):1−52, 2024. Abstract Gaussian denoising has emerged as a powerful method for constructing simulation-free continuous normalizing flows for generative modeling. Despite their empirical successes, theoretical properties of these flows and…

Gaussian Mixture Models with Rare Events Xuetong Li, Jing Zhou, Hansheng Wang; 25(252):1−40, 2024. Abstract We study here a Gaussian mixture model (GMM) with rare events data. In this case, the commonly used Expectation-Maximization (EM) algorithm exhibits extremely slow numerical…

On the Concentration of the Minimizers of Empirical Risks Paul Escande; 25(251):1−53, 2024. Abstract Obtaining guarantees on the convergence of the minimizers of empirical risks to the ones of the true risk is a fundamental matter in statistical learning. Instead…