When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training

• URL: http://arxiv.org/abs/2602.21454v1
• Date: Wed, 25 Feb 2026 00:15:13 GMT
• Title: When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training
• Authors: Alexander Morgan, Ummay Sumaya Khan, Lingjia Liu, Lizhong Zheng,
• Abstract summary: We analytically examine why learning recurrent poles does not provide tangible benefits in data and empirically offer real-time learning scenarios.<n>We show that fixed-pole networks achieve superior performance with lower training complexity, making them more suitable for online real-time tasks.
• Score: 58.25341036646294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering operation governed by both feedforward weights and recurrent poles. While, in principle, all parameters including pole locations can be optimized via backpropagation through time (BPTT), such joint learning incurs substantial computational overhead and is often impractical for applications with limited training data. Echo state networks (ESNs) mitigate this limitation by fixing the recurrent dynamics and training only a linear readout, enabling efficient and stable online adaptation. In this work, we analytically and empirically examine why learning recurrent poles does not provide tangible benefits in data-constrained, real-time learning scenarios. Our analysis shows that pole learning renders the weight optimization problem highly non-convex, requiring significantly more training samples and iterations for gradient-based methods to converge to meaningful solutions. Empirically, we observe that for complex-valued data, gradient descent frequently exhibits prolonged plateaus, and advanced optimizers offer limited improvement. In contrast, fixed-pole architectures induce stable and well-conditioned state representations even with limited training data. Numerical results demonstrate that fixed-pole networks achieve superior performance with lower training complexity, making them more suitable for online real-time tasks.

Related papers

• Online Continual Learning for Time Series: a Natural Score-driven Approach [2.8989185098518626]
  Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge.<n>Online time series forecasting (OTSF) is a real-world problem where data evolve in time and success depends on both rapid adaptation and long-term memory.<n>This paper aims to strengthen the theoretical and practical connections between time series methods and OCL.
  arXiv  Detail & Related papers  (2026-01-19T10:31:01Z)
• Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data [89.96277093034547]
  We introduce EntroDrop, an entropy-guided token dropout method that functions as structured data regularization.<n>We show that EntroDrop consistently outperforms standard regularization baselines and maintains robust performance throughout extended multi-epoch training.
  arXiv  Detail & Related papers  (2025-12-29T12:35:51Z)
• Offline Reinforcement Learning for End-to-End Autonomous Driving [1.2891210250935148]
  End-to-end (E2E) autonomous driving models take only camera images as input and directly predict a future trajectory.<n>Online reinforcement learning (RL) could mitigate IL-induced issues.<n>We introduce a camera-only E2E offline RL framework that performs no additional exploration and trains solely on a fixed simulator dataset.
  arXiv  Detail & Related papers  (2025-12-21T09:21:04Z)
• oRANS: Online optimisation of RANS machine learning models with embedded DNS data generation [0.0]
  Closures trained in the conventional offline paradigm tend to overfit and fail to generalise to new regimes.<n>We introduce an online optimisation framework for DL-based Navier-Stokes (RANS) closures which seeks to address the challenge of limited high-fidelity datasets.
  arXiv  Detail & Related papers  (2025-10-03T13:19:01Z)
• Fast Training of Recurrent Neural Networks with Stationary State Feedbacks [48.22082789438538]
  Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers.<n>We propose a novel method that replaces BPTT with a fixed gradient feedback mechanism.
  arXiv  Detail & Related papers  (2025-03-29T14:45:52Z)
• Estimating Post-Synaptic Effects for Online Training of Feed-Forward SNNs [0.27016900604393124]
  Facilitating online learning in spiking neural networks (SNNs) is a key step in developing event-based models. We propose Online Training with Postsynaptic Estimates (OTPE) for training feed-forward SNNs. We show improved scaling for multi-layer networks using a novel approximation of temporal effects on the subsequent layer's activity.
  arXiv  Detail & Related papers  (2023-11-07T16:53:39Z)
• A Sequential Meta-Transfer (SMT) Learning to Combat Complexities of Physics-Informed Neural Networks: Application to Composites Autoclave Processing [1.6317061277457001]
  PINNs have gained popularity in solving nonlinear partial differential equations. PINNs are designed to approximate a specific realization of a given PDE system. They lack the necessary generalizability to efficiently adapt to new system configurations.
  arXiv  Detail & Related papers  (2023-08-12T02:46:54Z)
• Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism [65.46524775457928]
  offline reinforcement learning seeks to utilize offline/historical data to optimize sequential decision-making strategies. We study the statistical limits of offline reinforcement learning with linear model representations.
  arXiv  Detail & Related papers  (2022-03-11T09:00:12Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• What training reveals about neural network complexity [80.87515604428346]
  This work explores the hypothesis that the complexity of the function a deep neural network (NN) is learning can be deduced by how fast its weights change during training. Our results support the hypothesis that good training behavior can be a useful bias towards good generalization.
  arXiv  Detail & Related papers  (2021-06-08T08:58:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.