Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions
Sehwan Kim, Yan Sun, Faming Liang
stat.ML, cs.LG, math.ST
Submitted: 2026-06-22
Code: https://github.com/justinbellucci/cnn-visualizations-pytorch
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
- Deep Learning Scaling is Predictable, Empirically
- Scaling Laws for Neural Language Models
- Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
- A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features
- Very Deep Convolutional Networks for Large-Scale Image Recognition
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches