The paper surveys continuous‑time (CT) machine learning, a framework for modeling temporal dynamics as continuous processes, especially useful when data are sampled irregularly or over long horizons. It introduces a unified taxonomy that groups major CT methods by their underlying mathematical formulations and shows how different architectural choices—such as vector‑field parameterization, stochasticity, memory mechanisms, and discretization—relate these families. The survey compares training algorithms, optimization strategies, failure modes, computational complexity, and benchmarks, reviews supporting software ecosystems, and outlines open challenges and future research directions.
By Waleed Razzaq, Yun-Sheng Zhao, Yun-Bo Zhao
arXiv:2607. 28035v1 Announce Type: new Abstract: Irregular multivariate time series are widely encountered in applications such as healthcare monitoring, human activity recognition, and environmental sensing.
By Tianen Shen, Zhengyu Li, Yutong Li, Xiangfei Qiu, Xingjian Wu, Bin Yang, Jilin Hu
arXiv:2607. 05280v1 Announce Type: new Abstract: Many real-world systems evolve continuously, yet most machine learning models interpret time series as discrete sequences.
By Benjamin Walker
arXiv:2509. 23052v2 Announce Type: replace Abstract: We present a new meta-learning method to determine the optimal learning rate schedule for gradient descent.
By Matt L. Sampson, Peter Melchior
arXiv:2606. 03917v1 Announce Type: cross Abstract: As Moore's law reaches its limits, Ising machines offer a promising alternative computing approach for difficult optimization problems.
By Stijn Van Vooren, Guy Van der Sande, Guy Verschaffelt
arXiv:2606. 01028v1 Announce Type: new Abstract: Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals.
By Yuepeng Wang, Ken Kawano, Yongqi Zhou, Yoshihiko Fujisawa, Richard Weiss, Akifumi Wachi, Katsuki Fujisawa, Ying Chen, Mehrshad Sadria, Xin Liu, Kyoung-Sook Kim, Xiao Hu, Sebastien Gros, Xun Shen
arXiv:2608. 20044v1 Announce Type: new Abstract: Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments.
By Aur\'elien Renault, Alexis Bondu, Antoine Cornu\'ejols, Vincent Lemaire
ExpTest is an autonomous learning‑rate controller that uses the training loss curve as an online signal to perform sequential statistical tests on theoretically motivated windows, detecting convergent behavior and triggering learning‑rate reductions. It combines a covariance‑based initial learning‑rate estimate, curvature‑motivated window sizing, and a two‑phase test‑driven decay, relying on the approximately exponential decay predicted under linearized network dynamics. Experiments on regression, classification, forecasting, and natural‑language tasks across various architectures show that ExpTest achieves competitive performance compared to hand‑tuned SGD baselines and recent learning‑rate‑free methods, without requiring manual initial learning‑rate selection or predefined scheduling.
By Zan Chaudhry, Naoko Mizuno
arXiv:2406. 06629v2 Announce Type: replace Abstract: This survey examines key advancements in designing features to represent optimization problem instances, algorithm instances, and their interactions within the context of single-objective continuous black-box optimization.
By Gjorgjina Cenikj, Ana Nikolikj, Ga\v{s}per Petelin, Niki van Stein, Carola Doerr, Tome Eftimov
arXiv:2606. 12240v1 Announce Type: cross Abstract: Multivariate time-series data often exhibit complex temporal dependencies, irregular sampling, and heterogeneous dynamics across multiple time scales, making accurate sequence modeling particularly challenging.
By Shilong Zong, Almuatazbellah Boker, Hoda Eldardiry
Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments. Yet, most existing methods assume stationarity and rely on separable designs, where classification and triggering are optimized independently, an assumption that fundamentally limits their adaptability under drift.
arXiv:2607. 05908v1 Announce Type: new Abstract: Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems.
By Robin Holzinger (Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA), Riccardo Colletti (Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA)