We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maximum likelihood is the most common approach to training CRFs, it ignores the inherent structure of the task's loss function. We describe alternatives to maximum likelihood which take that loss into account. These include a novel adaptation of a loss upper bound from the structured SVMs literature to the CRF context, as well as a new loss-inspired KL divergence objective which relies on the probabilistic nature of CRFs. These loss-sensitive objectives are compared to maximum likelihood using ranking as a benchmark task. This comparison confirms the importance of incorporating loss information in the probabilistic training of CRFs, with the loss-inspired KL outperforming all other objectives.
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
School of Computation, Information and Technology, Technical University of Munich（计算、信息与技术学院，慕尼黑技术大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Open Set Recognition with Conditional Probabilistic Generative Models
Nanyang Technological University（南洋理工大学）
深度神经网络在广泛的视觉理解任务中取得了突破。阻碍其现实应用的一个典型挑战是，在测试阶段可能会将未知样本输入系统，但传统的深度神经网络会错误地将这些未知样本识别为已知类别之一。开集识别（Open Set Recognition，OSR）是解决这一问题的一种有效方法，它要求开集分类器具有拒绝未知样本的灵活性，同时在已知类别中保持较高的分类精度。概率生成模型，如变分自编码器（VAE）和对抗性自编码器（AAE），是检测未知数的流行方法，但它们不能为已知分类提供判别表示。在本文中，我们提出了一个新的框架，称为条件概率生成模型（CPGM），开集识别。我们工作的核心见解是将判别信息添加到概率生成模型中，使得所提出的模型不仅可以检测未知样本，还可以通过强制不同的潜在特征近似条件高斯分布来分类已知类别。我们讨论了许多模型变体，并提供了全面的实验来研究它们的特性。在多个基准数据集上的实验结果表明，该方法的性能明显优于基线，达到了新的最先进的性能。
Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting
Graduate University of Advanced Studies & The Institute of Statistical Mathematics（高级研究大学及统计数学研究所）；East China Normal University（华东师范大学）；The Institute of Statistical Mathematics（统计数学研究所）
Probabilistic Conformal Prediction with Approximate Conditional Validity
Lagrange Mathematics and Computing Research Center（拉格朗日数学与计算研究中心）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Ecole Polytechnique（巴黎综合理工学院）
Probabilistic data quality assessment for structural monitoring data via outlier-resistant conditional diffusion model
Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology（工业和信息化部智能防灾减灾重点实验室）；School of Civil Engineering, Harbin Institute of Technology（哈尔滨工业大学土木工程学院）；Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education（教育部结构动力行为与控制重点实验室）；Harbin Institute of Technology（哈尔滨工业大学）
Conformalised Conditional Normalising Flows for Joint Prediction Regions in time series
Hasso Plattner Institute for Digital Engineering（哈索·普拉特纳数字工程学院）；University of California, Irvine（加利福尼亚大学欧文分校）；Hasso Plattner Institute for Digital Health at the Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院哈索·普拉特纳数字健康研究所）
Cost-sensitive probabilistic predictions for support vector machines
University Carlos III of Madrid（马德里卡洛斯三世大学）；Instituto de Matemáticas de la Universidad de Sevilla（塞维利亚大学数学研究所）；University of Sevilla（塞维利亚大学）；University of Cádiz（加的斯大学）
Colored Markov Random Fields for Probabilistic Topological Modeling
Statistical Sciences Dept., Sapienza University of Rome, Italy（统计科学系，罗马萨皮恩扎大学）；DIET Dept., Sapienza University of Rome, Italy（DIET系，罗马萨皮恩扎大学）；DIAG Dept., Sapienza University of Rome, Italy（DIAG系，罗马萨皮恩扎大学）
