No article text was recorded for this version.
non-linear implicit bias
Version 1 of 154 papers57 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Momentum Doesn't Change the Implicit Bias
- Blog: Faster Margin Maximization Rates for Generic Optimization Methods
- Blog: Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
- Blog: Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias
- Blog: Towards Understanding Sharpness-Aware Minimization
- Blog: Implicit Bias of Linear Equivariant Networks
- Blog: Implicit Regularization for Group Sparsity
- Blog: When will gradient methods converge to max‐margin classifier under ReLU models?
- Blog: Understanding the Under-Coverage Bias in Uncertainty Estimation
- Blog: Characterizing the implicit bias via a primal-dual analysis
- Blog: Towards Understanding Learning in Neural Networks with Linear Teachers
- Blog: Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
- Blog: Training Efficiency and Robustness in Deep Learning
- Blog: Distributed Gradient Descent with Many Local Steps in Overparameterized Models
- Blog: Approximately Equivariant Graph Networks
- Blog: Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
- Blog: Gradient descent follows the regularization path for general losses
- Blog: Fast rates for noisy interpolation require rethinking the effect of inductive bias
- Blog: Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently
- Blog: Implicit Bias of Linear Equivariant Networks
- Blog: The Implicit Bias of Adam on Separable Data
- Blog: Graph Neural Networks Use Graphs When They Shouldn't
- Blog: On the spectral bias of two-layer linear networks
- Blog: Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks
- Blog: Implicit Bias of the Step Size in Linear Diagonal Neural Networks
- Blog: Adversarial Training with Large Step Sizes: Implicit Bias and Evolution of Sharpness
- Blog: Convergence of SGD in Learning ReLU Models with Separable Data
- Blog: Towards Understanding Sharpness-Aware Minimization
- Blog: Fast rates for noisy interpolation require rethinking the effect of inductive bias
- Blog: Convergence of Gradient Descent on Separable Data
- Blog: The Implicit Bias of AdaGrad on Separable Data
- Blog: Applying statistical learning theory to deep learning
- Blog: Accurate Inference for Adaptive Linear Models
- Blog: Training invariances and the low-rank phenomenon: beyond linear networks
- Blog: Efficiency Calibration of Implicit Regularization in Deep Networks via Self-paced Curriculum-Driven Singular Value Selection
- Blog: How Does Adaptive Optimization Impact Local Neural Network Geometry?
- Blog: Implicit Regularization Towards Rank Minimization in ReLU Networks
- Blog: Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
- Blog: Implicit Regularization in Matrix Factorization
- Blog: Implicit Bias of Gradient Descent based Adversarial Training on Separable Data
- Blog: ImpMIA: Leveraging Implicit Bias for Membership Inference Attack under Realistic Scenarios
- Blog: Implicit Bias of Linear RNNs
- Blog: Implicit Regularization in Tensor Factorization
- Blog: The Implicit Bias of Gradient Descent on Separable Data
- Blog: Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
- Blog: Reparameterizing Mirror Descent as Gradient Descent
- Blog: ReLU Neural Networks with Linear Layers Are Biased towards Single- and Multi-index Models
- Blog: Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm
- Blog: Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
- Blog: Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
- Blog: Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability
- Blog: SGD with Large Step Sizes Learns Sparse Features
- Blog: Does Momentum Change the Implicit Regularization on Separable Data?
- Blog: The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
History & citation
Current · Permanent link
- This direction split from Implicit Bias of Gradient Descent in Overparameterized Models (78% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_non_linear_implicit_bias_d0e298f6,
title = {non-linear implicit bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-linear-implicit-bias/rdr_d0e298f6c70347fbbaad8a173992c8e9},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_non_linear_implicit_bias_d0e298f6_v1,
title = {non-linear implicit bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-linear-implicit-bias/rdr_d0e298f6c70347fbbaad8a173992c8e9/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}