No article text was recorded for this version.
architectural inductive bias (architectural implicit bias)
Version 1 of 144 papers53 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Implicit Bias of Gradient Descent on Linear Convolutional Networks
- Blog: Reparameterizing Mirror Descent as Gradient Descent
- Blog: Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
- Blog: What they do when in doubt: a study of inductive biases in seq2seq learners
- Blog: The Price of Implicit Bias in Adversarially Robust Generalization
- Blog: Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time
- Blog: On the Implicit Bias in Deep-Learning Algorithms
- Blog: Is SGD a Bayesian sampler? Well, almost
- Blog: Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives
- Blog: On the Frequency-bias of Coordinate-MLPs
- Blog: Implicit Regularization for Group Sparsity
- Blog: Rotation Synchronization via Deep Matrix Factorization
- Blog: Bayesian Deep Learning and a Probabilistic Perspective of Generalization
- Blog: A unifying view on implicit bias in training linear neural networks
- Blog: Understanding Generalization and Optimization Performance of Deep CNNs
- Blog: The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings
- Blog: On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
- Blog: Depth Without the Magic: Inductive Bias of Natural Gradient Descent
- Blog: Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression
- Blog: Robustness of Nonlinear Representation Learning
- Blog: Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization
- Blog: Distinguishing rule and exemplar-based generalization in learning systems
- Blog: Rejoinder: “Nonparametric regression using deep neural networks with ReLU activation function”
- Blog: Explaining Grokking in Transformers through the Lens of Inductive Bias
- Blog: The Riemannian Geometry associated to Gradient Flows of Linear Convolutional Networks
- Blog: Understanding Prompt Tuning and In-Context Learning via Meta-Learning
- Blog: Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression
- Blog: Transformers Learn Low Sensitivity Functions: Investigations and Implications
- Blog: Algorithmic Capabilities of Random Transformers
- Blog: Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias
- Blog: Feature Learning and Signal Propagation in Deep Neural Networks
- Blog: Quantifying Symmetries: How Optimisers Impact the Functional Dimension
- Blog: In-Context Learning through the Bayesian Prism
- Blog: The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation
- Blog: Representation Costs of Linear Neural Networks: Analysis and Design
- Blog: Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models
- Blog: Multiclass learning with margin: exponential rates with no bias-variance trade-off
- Blog: Generalization in diffusion models arises from geometry-adaptive harmonic representations
- Blog: Explicit Regularization in Overparametrized Models via Noise Injection
- Blog: Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
- Blog: The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
- Blog: Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation
- Blog: Winnowing with Gradient Descent
- Blog: Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_inductive_bias_architectur_afb6843f,
title = {architectural inductive bias (architectural implicit bias)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-inductive-bias-architectural-implicit-bias/rdr_afb6843fb5f54ea6af400ae4d80498c8},
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_architectural_inductive_bias_architectur_afb6843f_v1,
title = {architectural inductive bias (architectural implicit bias)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-inductive-bias-architectural-implicit-bias/rdr_afb6843fb5f54ea6af400ae4d80498c8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}