Skip to content
conftrace_

over-parametrized

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

information-theoretic reduction (1) proportional regime (1) tubal tensor product (1) classification layer (1) low tubal rank (1) random initialization (1) linear model (1) implicit regularization (1) deep neural network (1) variational training (1)

Papers

Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent ICML 2025 Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime COLT 2025 Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks ICML 2024