Learning curves in natural and artificial systems
eess.SY, cs.LG, cs.SY
Submitted: 2026-11-03
Updated: 2026-11-03
Journal ref: Novikov D. (2026) Learning curves in natural and artificial systems // Large-scale Systems Control. Vol. 123. P.7-56
License: http://creativecommons.org/licenses/by/4.0/
The gist: A general mathematical model of experience formation is considered, in which the learning level is defined as the probability that the next value of the uncertainty factor has already been mastered…
Terminology
Abstract
A general mathematical model of experience formation is considered, in which the learning level is defined as the probability that the next value of the uncertainty factor has already been mastered and not forgotten. Within this model the shape of the learning curve is derived, and it turns out to be determined primarily by the distribution of situation occurrence: a uniform distribution yields an exponential curve, whereas a power-law distribution yields a power-law curve whose exponent equals the ratio of the distribution exponent to that same exponent increased by one. Both mechanisms generating power-law curves, established earlier in the analysis of debugging, assembly and repair activities, are shown to have been independently rediscovered in deep learning theory as the "frequency" and "spectral" mechanisms of scaling laws for artificial neural networks, while the exponential curves of machine learning (contraction operators, strongly convex optimization, stationary reinforcement) are generated by the same constancy of the contraction coefficient that was revealed half a century earlier in models of radioactive decay, the first-order lag element, and others. A solution is given for the problem of choosing a training distribution that differs from the deployment distribution. A methodological consequence is discussed: three distinct mechanisms generate curves indistinguishable in shape, so an observed learning curve does not allow one to judge the "internal" structure of the learning system.
Sources
- Deep Learning Scaling is Predictable, Empirically
- Learning Curve Theory
- Scaling Laws for Neural Language Models
- Learning Curves for Decision Making in Supervised Machine Learning: A Survey
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Freeze-Thaw Bayesian Optimization
- Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance
Related papers
- Industrial Load Modeling and Optimization for Market-Based Interaction with Power Systems
- Exact and Approximate Convex Reformulation of Linear Stochastic Optimal Control with Chance Constraints
- Certified Set Convergence for Piecewise Affine Systems
- Symbolic Control for Stochastic Systems via Finite Parity Games
- Multiobjective optimization-based design and dispatch of islanded, hybrid microgrids for remote, off-grid communities in sub-Saharan Africa
- Physiology-informed layered sensing for intelligent human-exoskeleton interaction