No article text was recorded for this version.
implicit bias
Version 1 of 1223 papers241 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Optimal Implicit Bias in Linear Regression
- Blog: The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
- Blog: Is SGD a Bayesian sampler? Well, almost
- Blog: Faster margin maximization rates for generic and adversarially robust optimization methods
- Blog: Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
- Blog: On the Minimal Error of Empirical Risk Minimization
- Blog: Deep Nets Don't Learn via Memorization
- Blog: Stronger generalization bounds for deep nets via a compression approach
- Blog: Gradient descent for deep matrix factorization: Dynamics and implicit bias towards low rank
- Blog: A Bayesian Perspective on Training Speed and Model Selection
- Blog: Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
- Blog: A Unified Approach to Controlling Implicit Regularization via Mirror Descent
- Blog: Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU Nets
- Blog: In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
- Blog: Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
- Blog: Deep learning generalizes because the parameter-function map is biased towards simple functions
- Blog: On the Implicit Bias of Gradient Descent for Temporal Extrapolation
- Blog: Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias
- Blog: A Bayesian Perspective on Training Speed and Model Selection
- Blog: Implicit Bias of Polyak and Line-Search Step Sizes on Linear Classification with Separable Data
- Blog: When Will Gradient Methods Converge to Max-margin Classifier under ReLU Models?
- Blog: Is Your Diffusion Model Actually Denoising?
- Blog: Gradient dynamics of single-neuron autoencoders on orthogonal data
- Blog: Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization
- Blog: Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
- Blog: The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
- Blog: Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction
- Blog: Composing Global Optimizers to Reasoning Tasks via Algebraic Objects in Neural Nets
- Blog: Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
- Blog: Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
- Blog: Simplicity Bias in 1-Hidden Layer Neural Networks
- Blog: Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate
- Blog: Characterizing Implicit Bias in Terms of Optimization Geometry
- Blog: On the loss landscape of a class of deep neural networks with no bad local valleys
- Blog: Quantifying and Optimizing Simplicity via Polynomial Representations
- Blog: SGD Generalizes Better Than GD (And Regularization Doesn't Help)
- Blog: Global Minima of DNNs: The Plenty Pantry
- Blog: SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network
- Blog: Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
- Blog: Gradient Descent Converges to Ridgelet Spectrum
- Blog: Implicit Bias of Next-Token Prediction
- Blog: On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing
- Blog: On The Power of Deep But Naive Partial Label Learning
- Blog: Overparameterization and Generalization Error: Weighted Trigonometric Interpolation
- Blog: A unifying view on implicit bias in training linear neural networks
- Blog: Characterizing the implicit bias via a primal-dual analysis
- Blog: On the Dynamics Under the Unhinged Loss and Beyond
- Blog: A Principle of Least Action for the Training of Neural Networks
- Blog: On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
- Blog: Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization
- Blog: Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
- Blog: Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
- Blog: Generalization bounds via distillation
- Blog: On the Implicit Bias of Dropout
- Blog: The inductive bias of ReLU networks on orthogonally separable data
- Blog: Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
- Blog: Towards Understanding Knowledge Distillation
- Blog: Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
- Blog: Generalization by design: Shortcuts to Generalization in Deep Learning
- Blog: Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach
Showing 60 of 223 papers.
History & citation
Current · Permanent link
- This direction split from Implicit Bias of Gradient Descent in Overparameterized Networks (54% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_implicit_bias_b816d99b,
title = {implicit bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/implicit-bias/rdr_b816d99be8a14724a18dfcd5f1381e52},
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_implicit_bias_b816d99b_v1,
title = {implicit bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/implicit-bias/rdr_b816d99be8a14724a18dfcd5f1381e52/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}