Pith. sign in

REVIEW 8 cited by

Learning Continually by Spectral Regularization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.06811 v2 pith:CERYEAIN submitted 2024-06-10 cs.LG

classification cs.LG
keywords learningcontinualspectraltrainabilityperformancebetterregularizationregularizer
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Loss of plasticity is a phenomenon where neural networks can become more difficult to train over the course of learning. Continual learning algorithms seek to mitigate this effect 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. From this perspective, we derive a new spectral regularizer for continual learning that better sustains these beneficial initialization properties throughout training. In particular, the regularizer keeps the maximum singular value of each layer close to one. Spectral regularization directly ensures that gradient diversity is maintained throughout training, which promotes continual trainability, while minimally interfering with performance in a single task. 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. Spectral regularization is less sensitive to hyperparameters while demonstrating better training in individual tasks, sustaining trainability as new tasks arrive, and achieving better generalization performance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    KNIFE targets stagnant neurons in MARL value factorization by replacing them with a composite of frozen, re-initialized, and compensating units to restore plasticity while preserving cooperation knowledge.

  2. Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    On-policy distillation gains efficiency from early foresight in module focus and update directions, enabling EffOPD to accelerate training 3x with comparable performance.

  3. Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    On-policy distillation gains efficiency from early foresight in module allocation and low-rank update directions, enabling EffOPD to accelerate training by 3x via adaptive extrapolation without extra modules or tuning.

  4. Rotation-Preserving Supervised Fine-Tuning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    RPSFT improves the in-domain versus out-of-domain performance trade-off during LLM supervised fine-tuning by penalizing rotations in pretrained singular subspaces as a proxy for loss-sensitive directions.

  5. Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    VLMs possess a latent 3D scene topology subspace corresponding to Laplacian eigenmaps that can be causally shaped via Dirichlet energy regularization to improve spatial task performance by up to 12.1%.

  6. Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    On-policy distillation gains efficiency from early foresight in module allocation and update directions, which the proposed EffOPD method exploits for 3x faster training with comparable performance.

  7. Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    GXD estimates the first-order functional cost of replacing a neuron via gradient attribution to make adaptive resets more reliable for preserving plasticity in continual learning.

  8. Reinitializing weights vs units for maintaining plasticity in neural networks

    cs.NE 2025-07 conditional novelty 5.0 of 10

    Selective weight reinitialization, which resets the least useful weights, maintains plasticity in small and layer-normalized networks where unit-level reinitialization methods fail.

Pith tools