REVIEW 20 cited by
Feature Learning in Infinite-Width Neural 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
Feature Learning in Infinite-Width Neural Networks
read the original abstract
As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK parametrization). However, we show that the standard and NTK parametrizations of a neural network do not admit infinite-width limits that can learn features, which is crucial for pretraining and transfer learning such as with BERT. We propose simple modifications to the standard parametrization to allow for feature learning in the limit. Using the *Tensor Programs* technique, we derive explicit formulas for such limits. On Word2Vec and few-shot learning on Omniglot via MAML, two canonical tasks that rely crucially on feature learning, we compute these limits exactly. We find that they outperform both NTK baselines and finite-width networks, with the latter approaching the infinite-width feature learning performance as width increases. More generally, we classify a natural space of neural network parametrizations that generalizes standard, NTK, and Mean Field parametrizations. We show 1) any parametrization in this space either admits feature learning or has an infinite-width training dynamics given by kernel gradient descent, but not both; 2) any such infinite-width limit can be computed using the Tensor Programs technique. Code for our experiments can be found at github.com/edwardjhu/TP4.
Forward citations
Cited by 20 Pith papers
-
Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse
Noisy SGD in the mean-field regime forces wide multivariate ReLU networks to an effective width of at most 2P-1, yielding a continuous piecewise-affine predictor whose hyperplanes are non-redundant with respect to the...
-
Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product
In double asymptotic limits, the squared singular value process of non-square matrix products obeys geometric Dyson Brownian motion whose T-transform solves a Burgers equation, producing the free log-normal law via fr...
-
Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product
In a sequential d,n→∞ then m→∞ limit with dm/n fixed, the spectrum of a deep linear Gaussian network's feature covariance converges to the free log-normal law, whose T-transform solves a Burgers equation.
-
Convergence of Gradient Descent for General Neural Network Architectures Beyond the NTK Regime
Proves GD convergence to stationary point neighborhoods for general NN architectures beyond NTK via block-level analysis, analyticity, and local smoothness conditions.
-
Channel Location Constrains the Auditability of Subliminal Learning
Auditability of subliminal learning is constrained by channel location, with initialization-dependent body channels allowing pre-training screens while vocabulary geometry and conditional body channels evade them.
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
Asymmetric Langevin Unlearning uses public data to suppress unlearning noise costs by O(1/n_pub²), enabling practical mass unlearning with preserved utility under distribution mismatch.
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
-
LoRA: Low-Rank Adaptation of Large Language Models
Adapting large language models by training only a low-rank decomposition BA added to frozen weight matrices matches full fine-tuning while cutting trainable parameters by orders of magnitude and adding no inference latency.
-
HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning
HPP decouples perception from reasoning in long-video VLMs by having an LLM run iterative programmatic probes on hierarchically segmented video, reporting gains on LongVideoBench, EgoSchema, VideoMME, and MLVU.
-
Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models
LLMs recover dominant binomial orders from corpora but align less closely with exact preference distributions, with preference strength partially encoded in middle-to-late layers and manipulable via steering.
-
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
Heavy-tail guided layerwise learning rates improve LLM convergence speed and generalization across LLaMA, GPT variants, AdamW and Muon optimizers from 60M to 1B parameters.
-
Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
Analytical theory of signal propagation in deep transformers at initialization yields quantitative prescriptions for weights and residuals to avoid rank and entropy collapse via Random Energy Model analogy.
-
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
MM1 models achieve state-of-the-art few-shot multimodal results by pre-training on a careful mix of image-caption, interleaved, and text-only data with optimized image encoders.
-
AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
AdaLoRA uses SVD-based pruning to allocate the parameter budget for low-rank fine-tuning updates according to per-matrix importance scores, yielding better performance than uniform allocation especially under tight budgets.
-
Pre-Strings Lectures on Artificial Intelligence
Lecture notes define neural-network field theory and survey how it recovers known QFT/string results plus applied AI techniques for string problems.
-
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
LLR uses heavy-tailed self-regularization theory to set per-layer learning rates in Transformers, yielding faster convergence and higher zero-shot accuracy than uniform rates across model scales.
-
Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
Pion is an optimizer that preserves the singular values of weight matrices in LLM training by applying orthogonal equivalence transformations.
-
Principled Design of Diffusion-based Optimizers for Inverse Problems
Reparameterizations create invariances in diffusion inverse-problem solvers, enabling hyperparameter reuse and accelerated inference via the OptDiff optimization framework.
-
CARE: Counselor-Aligned Response Engine for Online Mental-Health Support
CARE fine-tunes LLMs on counselor-validated crisis dialogues to produce responses with stronger semantic and strategic alignment to expert standards than general-purpose models in Hebrew and Arabic.
-
Foundation Models for Astrophysics
Astronomical 'foundation models' largely reuse transformers and self-supervised pretraining, but evidence of transfer to new instruments, populations, or tasks remains rare; the paper argues such evidence, not archite...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.