No article text was recorded for this version.
gradient starvation
Version 1 of 125 papers37 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the Learning Dynamics of Deep Neural Networks
- Blog: Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks
- Blog: DIVINE: Diverse-Inconspicuous Feature Learning to Mitigate Abridge Learning
- Blog: Gradient Starvation: A Learning Proclivity in Neural Networks
- Blog: The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning
- Blog: Why Fine-grained Labels in Pretraining Benefit Generalization?
- Blog: Complexity Matters: Feature Learning in the Presence of Spurious Correlations
- Blog: Fine-tuning with Very Large Dropout
- Blog: Intriguing Properties of Contrastive Losses
- Blog: The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning
- Blog: Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective
- Blog: Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling
- Blog: Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
- Blog: Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization
- Blog: Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
- Blog: Salience-Guided Cascaded Suppression Network for Person Re-Identification
- Blog: Variance-Covariance Regularization Improves Representation Learning
- Blog: Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
- Blog: Cardinality Restricted Boltzmann Machines
- Blog: Do generative models learn rare generative factors?
- Blog: Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
- Blog: Combinatorial Routing for Neural Trees
- Blog: Provable Benefit of Cutout and CutMix for Feature Learning
- Blog: Syntax vs. Semantics: How Transformers Learn Deep Dependencies
- Blog: Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification
History & citation
Current · Permanent link
- This direction split from Gradient Starvation and Feature Suppression (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_gradient_starvation_03f839ad,
title = {gradient starvation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-starvation/rdr_03f839ad5afe4293a3854ea0c7c94645},
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_gradient_starvation_03f839ad_v1,
title = {gradient starvation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-starvation/rdr_03f839ad5afe4293a3854ea0c7c94645/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}