No article text was recorded for this version.
depth-induced low-rank bias
Version 1 of 156 papers86 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
- Blog: Generalization Analysis of Deep Non-linear Matrix Completion
- Blog: Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
- Blog: DeNetDM: Debiasing by Network Depth Modulation
- Blog: Implicit Bias and Loss of Plasticity in Matrix Completion: Depth Promotes Low-Rankness
- Blog: Efficiency Calibration of Implicit Regularization in Deep Networks via Self-paced Curriculum-Driven Singular Value Selection
- Blog: Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
- Blog: The Persistence of Neural Collapse Despite Low-Rank Bias
- Blog: Rotation Synchronization via Deep Matrix Factorization
- Blog: Implicit Rank-Minimizing Autoencoder
- Blog: Implicit Regularization in Deep Matrix Factorization
- Blog: A unifying view on implicit bias in training linear neural networks
- Blog: Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
- Blog: Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
- Blog: Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
- Blog: The Low-Rank Simplicity Bias in Deep Networks
- Blog: How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
- Blog: Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
- Blog: The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models
- Blog: Multi-step Predictive Coding Leads To Simplicity Bias
- Blog: Spectral Geometric Matrix Completion
- Blog: The Low-Rank Simplicity Bias in Deep Networks
- Blog: Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
- Blog: Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks
- Blog: Implicit Bias of Linear Equivariant Networks
- Blog: Implicit Regularization in Deep Matrix Factorization
- Blog: What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models
- Blog: Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
- Blog: Understanding Surprising Generalization Phenomena in Deep Learning
- Blog: Deep Neural Regression Collapse
- Blog: Parallel Deep Neural Networks Have Zero Duality Gap
- Blog: Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
- Blog: Implicit Regularization in Tensor Factorization
- Blog: Efficient Low-Dimensional Compression of Overparameterized Models
- Blog: Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement
- Blog: Implicit Bias of Linear Equivariant Networks
- Blog: Parallel Deep Neural Networks Have Zero Duality Gap
- Blog: Precise Asymptotic Analysis of Deep Random Feature Models
- Blog: The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks
- Blog: Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
- Blog: Implicit Bias of Gradient Descent on Linear Convolutional Networks
- Blog: On Generalization Bounds for Neural Networks with Low Rank Layers
- Blog: Simplicity Bias in Overparameterized Machine Learning
- Blog: DeepTensor: Low-Rank Tensor Decomposition With Deep Network Priors
- Blog: Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff
- Blog: Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity
- Blog: Deep geometric matrix completion: Are we doing it right?
- Blog: Generalization Bounds for Rank-sparse Neural Networks
- Blog: Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
- Blog: Representation Costs of Linear Neural Networks: Analysis and Design
- Blog: Implicit Regularization Towards Rank Minimization in ReLU Networks
- Blog: DeNetDM: Debiasing by Network Depth Modulation
- Blog: Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
- Blog: Implicit Regularization in Deep Learning May Not Be Explainable by Norms
- Blog: Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment
- Blog: Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_depth_induced_low_rank_bias_665533bf,
title = {depth-induced low-rank bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/depth-induced-low-rank-bias/rdr_665533bfeeda4a4b9b19d1521d2aaabb},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_depth_induced_low_rank_bias_665533bf_v1,
title = {depth-induced low-rank bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/depth-induced-low-rank-bias/rdr_665533bfeeda4a4b9b19d1521d2aaabb/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}