No article text was recorded for this version.
mechanistic scaling theory
Version 2 of 2131 papers138 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Solvable Attention for Neural Scaling Laws
- Blog: Superposition Yields Robust Neural Scaling
- Blog: Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
- Blog: A Theoretical Survey on Foundation Models
- Blog: Beyond scaling curves: internal dynamics of neural networks through the NTK lens
- Blog: Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models
- Blog: Scaling Laws from the Data Manifold Dimension
- Blog: Understanding Artificial Neural Network's Behavior from Neuron Activation Perspective
- Blog: A Dynamical Model of Neural Scaling Laws
- Blog: Scaling and Generalization in Neural Networks: A Case Study
- Blog: The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws
- Blog: Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks
- Blog: Neural Entropy
- Blog: Interpolating between the gauge and Schrödinger pictures of quantum dynamics
- Blog: Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models
- Blog: Learning curves theory for hierarchically compositional data with power-law distributed features
- Blog: Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
- Blog: InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition
- Blog: Scaling and renormalization in high-dimensional regression
- Blog: Scaling Laws for Associative Memories
- Blog: Scaling Laws in Jet Classification
- Blog: A Resource Model For Neural Scaling Law
- Blog: Information-Theoretic Foundations for Neural Scaling Laws
- Blog: Deriving Neural Scaling Laws from the Statistics of Natural Language
- Blog: Two-point deterministic equivalence for SGD in random feature models
- Blog: A Constructive Prediction of the Generalization Error Across Scales
- Blog: Zipf’s Law Arises Naturally When There Are Underlying, Unobserved Variables
- Blog: Discovery of Unstable Singularities
- Blog: Efficient Hyperparameter Tuning via Trajectory Invariance Principle
- Blog: Mean field theory for deep dropout networks: digging up gradient backpropagation deeply
- Blog: Scaling description of generalization with number of parameters in deep learning
- Blog: The Quantization Model of Neural Scaling
- Blog: Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation
- Blog: On Power Laws in Deep Ensembles
- Blog: 4+3 Phases of Compute-Optimal Neural Scaling Laws
- Blog: Predictable Scale: Part I - Optimal Hyperparameter Scaling Law in Large Language Model Pretraining
- Blog: A Dynamical Model of Neural Scaling Laws
- Blog: Data Scaling Laws in NMT: The Effect of Noise and Architecture
- Blog: A Survey of Post-Training Scaling in Large Language Models
- Blog: Relative Scaling Laws for LLMs
- Blog: Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
- Blog: Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
- Blog: The Quantization Model of Neural Scaling
- Blog: Universal Features in the Growth Dynamics of Complex Organizations
- Blog: Deep Learning is Not So Mysterious or Different
- Blog: Initialization Schemes for Kolmogorov-Arnold Networks: An Empirical Study
- Blog: Universal One-third Time Scaling in Learning Peaked Distributions
- Blog: Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
- Blog: Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches
- Blog: Bayesian scaling laws for in-context learning
- Blog: Unlocking the Theory Behind Scaling 1-Bit Neural Networks
- Blog: Scaling Law with Learning Rate Annealing
- Blog: Unraveling the Mystery of Scaling Laws: Part I
- Blog: Contextures: Representations from Contexts
- Blog: Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra
- Blog: Deep Learning Scaling is Predictable, Empirically
- Blog: Large Language Models as Computable Approximations to Solomonoff Induction
- Blog: Scaling Laws for Precision in High-Dimensional Linear Regression
- Blog: Value-Based Deep RL Scales Predictably
- Blog: Why Larger Language Models Do In-context Learning Differently?
Showing 60 of 131 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_mechanistic_scaling_theory_27839d11,
title = {mechanistic scaling theory},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mechanistic-scaling-theory/rdr_27839d111a294f3d93115d40cabee452},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_mechanistic_scaling_theory_27839d11_v2,
title = {mechanistic scaling theory},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mechanistic-scaling-theory/rdr_27839d111a294f3d93115d40cabee452/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}