On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

9 results for “near-interpolators”

Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalizationstat.ML

Near-interpolating models grow norms quickly, affecting generalization.

problem Understanding the trade-off between interpolation and generalization in near-interpolating models.

method Random matrix theory and eigendecay analysis of data covariance matrix.

result Near-interpolating models exhibit rapid norm growth and worse generalization trade-offs.

near-interpolators norm growth generalization interpolation random matrix theory

2024-03-12abs ↗pdf ↗

Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolationstat.ML

Study reveals phase transition in neural networks near interpolation.

problem Understanding generalization and learning transitions in neural networks.

method Effective theory for approximating Bayes-optimal generalisation error.

result Unveils a discontinuous phase transition between universal and specialisation phases.

neural networks generalization phase transition shallow networks interpolation threshold

2025-01-30abs ↗pdf ↗

Statistical mechanics of extensive-width Bayesian neural networks near interpolationstat.ML

Statistical mechanics explains learning in large neural networks near interpolation.

problem Understanding the learning dynamics of large neural networks near interpolation.

method Statistical physics analysis of a two-layer network with generic weight distribution and activation function.

result Learning transitions and feature learning emerge as the number of data increases.

neural networks statistical mechanics Bayesian learning interpolation feature learning

2025-05-30abs ↗pdf ↗

Is Memorization Helpful or Harmful? Prior Information Sets the Thresholdstat.ML

The study finds that memorization is necessary or harmful depending on the prior distribution and noise level.

problem The impact of memorization on generalization in overparameterized models.

method An overparameterized linear model with general priors in a Bayesian setup.

result Explicit conditions for optimal generalization based on the prior distribution and noise level.

memorization generalization overparameterized Bayesian prior distribution

2026-02-10abs ↗pdf ↗

Optimistic Rates: A Unifying Theory for Interpolation Learning and Regularization in Linear Regressionstat.ML

Study optimizes linear regression analysis for high-dimensional settings.

problem Understanding high-dimensional linear regression with interpolation and regularization.

method Localized uniform convergence analysis of optimistic rates for linear regression.

result Recover guarantees for ridge and LASSO regression under random designs.

linear regression optimistic rates interpolation regularization high-dimensional settings

2021-12-08abs ↗pdf ↗

On the Universality of the Double Descent Peak in Ridgeless Regressionstat.ML

Lower bound proves ridgeless regression performs poorly near interpolation threshold.

problem Proving performance of ridgeless regression near interpolation threshold.

method Distribution-independent lower bound for mean squared error in noisy ridgeless linear regression.

result Lower bound implies ridgeless regression performs poorly near interpolation threshold.

ridgeless regression double descent label noise mean squared error interpolation threshold

2020-10-05abs ↗pdf ↗

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolationstat.ML

Statistical physics explains deep learning's feature learning capacity.

problem Understanding neural networks' ability to learn complex features.

method Study of a multi-layer perceptron in the interpolation regime.

result Optimal learning requires specialization across layers and neurons.

deep learning statistical physics neural networks feature learning interpolation

2025-10-28abs ↗pdf ↗

Dimension free ridge regressionmath.ST

New ridge regression bounds for high-dimensional data without proportional growth.

problem Moving beyond proportional asymptotics in high-dimensional statistics.

method Revisits ridge regression on i.i.d. data, allowing high-dimensional or infinite-dimensional feature vectors.

result Establishes non-asymptotic bounds approximating bias and variance of ridge regression.

ridge regression high-dimensional statistics random matrix theory Hilbert space overparametrization

2022-10-16abs ↗pdf ↗

Asymptotics of Random Feature Regression Beyond the Linear Scaling Regimestat.ML

The paper analyzes the performance of random feature regression in high dimensions.

problem Understanding how model complexity and generalization depend on the number of parameters and sample size.

method Investigates random feature ridge regression (RFRR) and compares it to kernel ridge regression (KRR).

result RFRR exhibits a trade-off between approximation and generalization power, with a double descent phenomenon at a specific point.

random feature regression ridge regression generalization double descent high-dimensional

2024-03-13abs ↗pdf ↗