SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.01585 · NeurIPS · 2025

The φ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control

Fanghui Liu, Yudong Chen, Lorenzo Rosasco, Yichen Wang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
yichenblue/norm-capacity canonical 4 of 4
FunctionStatusWhere it lives
compute_variance_beta Ran yichenblue/norm-capacity/src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py
pointer only (licence: NONE) · get_code("a4e46bd3edd53de7")
make_resnet18k Ran yichenblue/norm-capacity/src/Deep_NNs/deep_double_descent_ResNet18.py
pointer only (licence: NONE) · get_code("9e1fb7fda2faa973")
solve_lambda_star Ran yichenblue/norm-capacity/src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py
pointer only (licence: NONE) · get_code("2cd8c566c5b775b4")
solve_self_consistent_equations Ran yichenblue/norm-capacity/src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py
pointer only (licence: NONE) · get_code("290aa109a9a64251")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Understanding how the test risk scales with model complexity is a central question in machine learning. Classical theory is challenged by the learning curves observed for large over-parametrized deep networks. Capacity measures based on parameter count typically fail to account for these empirical observations. To tackle this challenge, we consider norm-based capacity measures and develop our study for random features based estimators, widely used as simplified theoretical models for more complex networks. In this context, we provide a precise characterization of how the estimator's norm concentrates and how it governs the associated test error. Our results show that the predicted learning curve admits a phase transition from under-to over-parameterization, but no double descent behavior. This confirms that more classical U-shaped behavior is recovered considering appropriate capacity measures based on models norms rather than size. From a technical point of view, we leverage deterministic equivalence as the key tool and further develop new deterministic quantities which are of independent interest.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.01585")
get_code_for_paper("2502.01585")
have("2502.01585")

Connect an agent — have() is free.