Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule. While existing adaptive optimizers schedule the LR automatically, they suffer from computational and memory overhead, incompatibility with regularization, and suboptimal LR choices. In this work, we introduce the ZENITH (Zero-overhead Evolution using Norm-Informed Training History) optimizer, which adapts the LR using the temporal evolution of the gradient norm. Image classification experiments spanning 6 CNN architectures and 6 benchmarks demonstrate that ZENITH achieves higher test accuracy in lower wall-clock time than baselines. It also yielded superior mAP in object detection, keypoint detection, and instance segmentation on MS COCO using the R-CNN family of models. Furthermore, its compatibility with regularization enables even better generalization.
Reconstruction-Based Anomaly Localization via Knowledge-Informed Self-Training
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Ningbo Research Institute, Zhejiang University（浙江大学宁波研究院）
Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks
Mathematical Sciences Institute and France-Australia Mathematical Sciences and Interactions ANU-CNRS International Research Lab（数学科学研究所和法国-澳大利亚数学科学与互动 ANU-CNRS 国际研究实验室）
Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias
Department of Computer Science and Engineering（计算机科学与工程系）；The Hong Kong University of Science and Technology（香港科学与技术大学）；School of Mathematical Sciences（数学科学学院）；Peking University（北京大学）；Department of Computer Science（计算机科学系）；University of Warwick（沃里克大学）；Industrial Engineering & Management Sciences（工业工程与管理科学）；Northwestern University（西北大学）
Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks
Department of Computational Applied Mathematics and Operations Research（计算应用数学与运筹学部门）；School of Data Science（数据科学学院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Cramér-Rao bound-informed training of neural networks for quantitative MRI
NYU School of Medicine（纽约大学医学院）；Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；Univ Paris Est Creteil（巴黎东克雷泰伊大学）；CNRS（法国国家科学研究中心）；NYU Center for Data Science（纽约大学数据科学中心）；NYU Courant Institute of Mathematical Sciences（纽约大学库朗数学科学研究所）
Physics-informed neural operator for parametric phase-field modelling of interfacial degradation and microstructural evolution
Tongji University, College of Civil Engineering（同济大学，土木工程学院）；Tongji University, State Key Laboratory of Disaster Reduction in Civil Engineering（同济大学，灾害防治工程重点实验室）
