arXiv (All)
open access
Double descent is the principle of least action
artificial-intelligencecomputational-physicsdata-analysismachine-learningstatistics-and-probabilitystatistics-theory
The test error of a model plotted against its number of parameters $d$ falls, peaks when the model can just fit the training data, and falls again, exhibiting the double descent phenomenon. We explain the phenomenon with statistical mechanics. The training trajectory of a stochastic gradient-based m
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Double descent is the principle of least action#965405
- Constant-Stepsize Stochastic Approximation: Finite-Time Convergence, Gaussian Approximation, and Tail Bounds#984992
- Some contributions to the study of the H2|2-model and the vertex-reinforced jump processes#676876
- Machine learning in parameter spaces beyond the Standard Model: Iterative methods for high-dimensional theory generation#1065593
- Nonlinear Drivers of Macroeconomic Tail Risk: A Threshold Stochastic Volatility-in-Mean VAR with Regime-Dependent Leverage#1063205
Record · ID 1014886
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive