REVIEW 6 cited by
Approaching Deep Learning through the Spectral Dynamics of Weights
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
Approaching Deep Learning through the Spectral Dynamics of Weights
read the original abstract
We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning. We identify a consistent bias in optimization across various experiments, from small-scale ``grokking'' to large-scale tasks like image classification with ConvNets, image generation with UNets, speech recognition with LSTMs, and language modeling with Transformers. We also demonstrate that weight decay enhances this bias beyond its role as a norm regularizer, even in practical systems. Moreover, we show that these spectral dynamics distinguish memorizing networks from generalizing ones, offering a novel perspective on this longstanding conundrum. Additionally, we leverage spectral dynamics to explore the emergence of well-performing sparse subnetworks (lottery tickets) and the structure of the loss surface through linear mode connectivity. Our findings suggest that spectral dynamics provide a coherent framework to better understand the behavior of neural networks across diverse settings.
Forward citations
Cited by 6 Pith papers
-
Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability
Neural networks admit large families of approximately equivalent solutions via neuron identifiability even without structural symmetry, enabling linear low-loss merging paths without prior alignment.
-
Low-Rank Decay for Grokking in Scale-Invariant Transformers: A Spectral-Geometric View
Low-Rank Decay induces effective-rank collapse in Query/Key matrices and widens the grokking regime on modular arithmetic tasks in scale-invariant Transformers.
-
Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
In an anisotropic random-matrix model of gradient flow, the teacher signal produces a transient BBP transition where the outlier eigenvalue emerges only in an intermediate time window before overfitting.
-
At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics
Embedding effective rank at grokking is a transient that overstates the converged floor by 3–5× (MLP) / 1.3–1.5× (transformer), and compression lags generalization by order T_grok, modulated by LayerNorm.
-
Does Weight Decay Enhance Training Stability?
Weight decay slows progressive sharpening at the edge of stability, inducing damped oscillations in CNNs and a phase transition to sub-2/η sharpness in MLPs driven by parameter-sharpness gradient alignment, yielding m...
-
Reversible Foundations: Training a 120B Sparse MoE through State-Preserving Scaling
A 120B sparse MoE model with 460 experts was trained on one 8-GPU node to loss 1.78 using reversible recurrence and state-preserving scaling from a 1.78B dense seed, with 5.93B active parameters.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.