发表机构
Ben-Gurion University; Northeastern University London（本-古里安大学; 东北大学伦敦校区）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对非平稳环境下高维模型在线学习计算困难的问题，提出AURA元学习框架，通过学习低维潜状态空间模型并利用扩展卡尔曼滤波实现高效在线适应，在无线接收机和图像分类任务上显著提升适应速度与精度。
AI 中文摘要
非平稳环境下的在线学习要求模型在严格的计算约束下从流式数据中快速适应。一种有原则的方法将在线学习视为贝叶斯状态跟踪，其中模型参数通过贝叶斯滤波顺序更新。然而，由于参数空间的高维性，直接将贝叶斯滤波器应用于现代深度模型在计算上是不可行的，这迫使现有方法依赖限制性近似或手动设计的低维子空间。在这项工作中，我们指出缺乏合适的低维动态表示是贝叶斯滤波在线学习的核心瓶颈。为此，我们提出了自适应更新通过表示适应（AURA），一种元学习框架，它离线学习一个低维潜状态空间模型，该模型控制分布偏移下最优模型参数的演化。在线适应随后通过在该学习到的潜空间中执行扩展卡尔曼滤波，并通过学习到的提升映射重建完整模型参数来完成，从而实现高效的单步在线适应，同时保持模型表达能力。在时变信道下的神经无线接收机在线适应和非平稳图像分类的评估中，AURA在适应速度、准确性和计算效率上显著优于现有的在线学习和贝叶斯滤波基线，表明适应感知的潜几何有利于高维模型中的有效贝叶斯在线学习。
英文摘要
Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled approach casts online learning as Bayesian state tracking, where model parameters are updated sequentially via Bayesian filtering. However, applying Bayesian filters directly to modern deep models is computationally prohibitive due to the high dimensionality of parameter space, forcing existing methods to rely on restrictive approximations or manually designed low-dimensional subspaces. In this work, we identify the absence of a suitable low-dimensional dynamical representation as the core bottleneck in Bayesian filtering-based online learning. Accordingly, we propose Adaptive Update through Representation Adaptation (AURA), a meta-learning framework that learns offline a low-dimensional latent state-space model governing the evolution of optimal model parameters under distribution shift. Online adaptation is then performed via extended Kalman filtering in this learned latent space followed by reconstruction of the full model parameters through a learned lifting map, enabling efficient single-step online adaptation while preserving model expressiveness. Evaluated on online adaptation of neural wireless receivers under time-varying channels and on non-stationary image classification, AURA shows substantial improvements in adaptation speed, accuracy, and computational efficiency over existing online learning and Bayesian filtering baselines, demonstrating that an adaptation-aware latent geometry is beneficial for effective Bayesian online learning in high-dimensional models.
CommentsAccepted at NeurIPS 2026
