SingularClip: Preventing Spectral Collapse to Maintain Plasticity in Continual and Reinforcement Learning

• URL: http://arxiv.org/abs/2608.18319v1
• Date: Tue, 18 Aug 2026 21:12:06 GMT
• Title: SingularClip: Preventing Spectral Collapse to Maintain Plasticity in Continual and Reinforcement Learning
• Abstract summary: We identify a novel source of plasticity loss due to the growing anisotropy of weight matrices' singular values during training.<n>We introduce SingularClip, a procedure that periodically clips the singular values of all weight matrices.<n>We show that SingularClip performs strongly against baselines across a range of tasks in both continual supervised learning and deep reinforcement learning.
• Score: 7.023073256176158
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticity. We identify a novel source of plasticity loss due to the growing anisotropy of weight matrices' singular values during training, and analyze this phenomenon both empirically and theoretically. To mitigate this issue, we introduce SingularClip, a procedure that periodically clips the singular values of all weight matrices. We show that SingularClip performs strongly against baselines across a range of tasks in both continual supervised learning and deep reinforcement learning.

Related papers

• On the Plasticity Collapse in Continual Machine Unlearning [26.744674850970625]
  Machine unlearning enables networks to selectively remove the influence of specific data in response to privacy and regulatory requirements.<n>While prior work largely studies single-shot unlearning, real-world systems must accommodate continual unlearning.<n>We show that continual unlearning operations accumulate geometric constraints in parameter space, leading to saturated subspaces that restrict future updates.
  arXiv  Detail & Related papers  (2026-08-30T02:33:40Z)
• Dispelling the Curse of Singularities in Neural Network Optimizations [22.05217959662069]
  We show that the gradient Frobenius norms are bounded by the top singular values of the weight matrices, and as training progresses, the mutually reinforcing growth of weight and representation singularities, relaxes these bounds, escalating the risk of sharp loss explosions.<n>To counter this, we propose Parametric Singularity Smoothing (PSS), a lightweight, flexible, effective method for smoothing the singular spectra of weight matrices.
  arXiv  Detail & Related papers  (2026-02-01T16:09:06Z)
• SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning [48.41770886055744]
  Federated Learning has seen an increased deployment in real-world scenarios recently.<n>The introduction of the so-called gradient inversion attacks has challenged its privacy-preserving properties.<n>We introduce SPEAR, which is based on a theoretical analysis of the gradients of linear layers with ReLU activations.<n>Our new attack, SPEAR++, retains all desirable properties of SPEAR, such as robustness to DP noise and FedAvg aggregation.
  arXiv  Detail & Related papers  (2025-10-28T09:06:19Z)
• Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning [14.196969540084929]
  We show that deep neural networks suffer from loss of plasticity in deep continual learning.<n>We introduce the notion of $tau$-trainability and show that current plasticity preserving algorithms can be unified under this framework.<n> Experiments on continual supervised and reinforcement learning tasks confirm that combining these two regularizers effectively preserves plasticity.
  arXiv  Detail & Related papers  (2025-09-26T13:28:53Z)
• Parseval Regularization for Continual Reinforcement Learning [46.92116826808205]
  Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks.<n>We propose to use Parseval regularization to preserve useful optimization properties and improve training in a continual reinforcement learning setting.
  arXiv  Detail & Related papers  (2024-12-10T06:19:21Z)
• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• Learning Continually by Spectral Regularization [45.55508032009977]
  Continual learning algorithms seek to mitigate loss of plasticity by sustaining good performance while maintaining network trainability. We develop a new technique for improving continual learning inspired by the observation that the singular values of the neural network parameters at initialization are an important factor for trainability during early phases of learning. We present an experimental analysis that shows how the proposed spectral regularizer can sustain trainability and performance across a range of model architectures in continual supervised and reinforcement learning settings.
  arXiv  Detail & Related papers  (2024-06-10T21:34:43Z)
• Disentangling the Causes of Plasticity Loss in Neural Networks [55.23250269007988]
  We show that loss of plasticity can be decomposed into multiple independent mechanisms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks.
  arXiv  Detail & Related papers  (2024-02-29T00:02:33Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Maintaining Plasticity in Deep Continual Learning [12.27972591521307]
  We provide demonstrations of loss of plasticity using datasets repurposed for continual learning as sequences of tasks. In ImageNet, binary classification performance dropped from 89% accuracy on an early task down to 77%. New algorithm -- continual backpropagation -- modifies conventional backpropagation to re-use less-used units after each example.
  arXiv  Detail & Related papers  (2023-06-23T23:19:21Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)

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.