REVIEW 4 cited by
The Low-Rank Simplicity Bias in Deep Networks
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
Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to their training data? In this work, we make a series of empirical observations that investigate and extend the hypothesis that deeper networks are inductively biased to find solutions with lower effective rank embeddings. We conjecture that this bias exists because the volume of functions that maps to low effective rank embedding increases with depth. We show empirically that our claim holds true on finite width linear and non-linear models on practical learning paradigms and show that on natural data, these are often the solutions that generalize well. We then show that the simplicity bias exists at both initialization and after training and is resilient to hyper-parameters and learning methods. We further demonstrate how linear over-parameterization of deep non-linear models can be used to induce low-rank bias, improving generalization performance on CIFAR and ImageNet without changing the modeling capacity.
Forward citations
Cited by 4 Pith papers
-
The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting
High-entropy (equilibrium) neural networks retain old knowledge far better than standard-trained networks after learning noisy data, even when both generalize perfectly.
-
When More is Less: Understanding Chain-of-Thought Length in LLMs
LLM accuracy follows an inverted U in chain-of-thought length, with an optimal length that grows with task difficulty and shrinks with model capability.
-
Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough
Verification of ML in fundamental physics is essential precisely when models enter statistical modeling, inference, or hypothesis testing, and is bounded by unavoidable inductive bias, sample complexity, and experimen...
-
Representation biases: will we achieve complete understanding by analyzing representations?
Feature representation biases in trained models can distort PCA, regression, RSA, and model-brain comparisons, so representational analyses may not reveal all of a system's computations.
Discussion (0). Continue with ORCID to comment.