REVIEW 6 cited by
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
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
read the original abstract
The recently discovered Neural Collapse (NC) phenomenon occurs pervasively in today's deep net training paradigm of driving cross-entropy (CE) loss towards zero. During NC, last-layer features collapse to their class-means, both classifiers and class-means collapse to the same Simplex Equiangular Tight Frame, and classifier behavior collapses to the nearest-class-mean decision rule. Recent works demonstrated that deep nets trained with mean squared error (MSE) loss perform comparably to those trained with CE. As a preliminary, we empirically establish that NC emerges in such MSE-trained deep nets as well through experiments on three canonical networks and five benchmark datasets. We provide, in a Google Colab notebook, PyTorch code for reproducing MSE-NC and CE-NC: at https://colab.research.google.com/github/neuralcollapse/neuralcollapse/blob/main/neuralcollapse.ipynb. The analytically-tractable MSE loss offers more mathematical opportunities than the hard-to-analyze CE loss, inspiring us to leverage MSE loss towards the theoretical investigation of NC. We develop three main contributions: (I) We show a new decomposition of the MSE loss into (A) terms directly interpretable through the lens of NC and which assume the last-layer classifier is exactly the least-squares classifier; and (B) a term capturing the deviation from this least-squares classifier. (II) We exhibit experiments on canonical datasets and networks demonstrating that term-(B) is negligible during training. This motivates us to introduce a new theoretical construct: the central path, where the linear classifier stays MSE-optimal for feature activations throughout the dynamics. (III) By studying renormalized gradient flow along the central path, we derive exact dynamics that predict NC.
Forward citations
Cited by 6 Pith papers
-
MaxSketch: Robust Distinct Counting in Streams via Random Projections
MaxSketch achieves O~(log n / ε²) memory for (1+ε)-approximate distinct counting in streams with geometric structure via max-linear random projections.
-
Residual Feature Integration is Sufficient to Prevent Negative Transfer
Residual feature integration with a trainable target-side encoder provably prevents negative transfer, achieving convergence rates no worse than training from scratch under informative target distributions.
-
Representation Collapse in Sequential Post-Training of Large Language Models
Sequential post-training of LLMs induces representation collapse that correlates with reduced plasticity, weaker generalization, and poorer calibration, with lightweight interventions tested to mitigate it.
-
Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension
Neural regression collapse occurs when last-layer feature intrinsic dimension falls below target intrinsic dimension, creating over-compressed and under-compressed regimes that govern generalization based on data quan...
-
The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
FACT is a first-order stationarity identity for weight matrices that matches or beats the Neural Feature Ansatz as a description of learned features at convergence.
-
There Will Be a Scientific Theory of Deep Learning
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universa...
Discussion (0). Sign in to comment.