No article text was recorded for this version.
architectural simplicity bias
Version 1 of 125 papers36 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Simplicity Bias in Overparameterized Machine Learning
- Blog: Deep learning generalizes because the parameter-function map is biased towards simple functions
- Blog: Bias in the arrival of variation can dominate over natural selection in Richard Dawkins's biomorphs
- Blog: Deep neural networks have an inbuilt Occam’s razor
- Blog: How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
- Blog: When do neural networks learn world models?
- Blog: Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
- Blog: Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
- Blog: Phenotype bias determines how natural RNA structures occupy the morphospace of all possible shapes
- Blog: Symmetry and simplicity spontaneously emerge from the algorithmic nature of evolution
- Blog: Network-to-Network Regularization: Enforcing Occam's Razor to Improve Generalization
- Blog: Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent
- Blog: The Low-Rank Simplicity Bias in Deep Networks
- Blog: RNA secondary structures are conserved but random
- Blog: Generalization on the Unseen, Logic Reasoning and Degree Curriculum
- Blog: Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks
- Blog: Self-assembly, modularity, and physical complexity
- Blog: Bounding phenotype transition probabilities via conditional complexity
- Blog: In-Context Learning through the Bayesian Prism
- Blog: Input–output maps are strongly biased towards simple outputs
- Blog: Random deep neural networks are biased towards simple functions
- Blog: Revisiting the Volume Hypothesis
- Blog: Neural Prior for Trajectory Estimation
- Blog: Free Lunch for Optimisation under the Universal Distribution
- Blog: Implicit regularization of dropout
History & citation
Current · Permanent link
- This direction split from The Inherent Simplicity Bias of Neural Architectures (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_simplicity_bias_529dfa4c,
title = {architectural simplicity bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-simplicity-bias/rdr_529dfa4cc7b847f28d4cbe40e46236c8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_architectural_simplicity_bias_529dfa4c_v1,
title = {architectural simplicity bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-simplicity-bias/rdr_529dfa4cc7b847f28d4cbe40e46236c8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}