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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

9 results for “non-interpolating”

Private optimization in the interpolation regime: faster rates and hardness resultscs.LG

Private optimization faster on interpolation problems with quadratic growth.

problem Private optimization in interpolation problems.

method Adaptive algorithm with improved sample complexity.

result Exponential improvement in private sample complexity for quadratic growth.

private optimization interpolation problems quadratic growth adaptive algorithm sample complexity

2022-10-31abs ↗pdf ↗

Learning Ability of Interpolating Deep Convolutional Neural Networksstat.ML

The study examines deep convolutional neural networks and their learning ability.

problem Understanding the learning ability of deep convolutional neural networks (DCNNs).

method Examines DCNNs under both underparameterized and overparameterized settings, using a novel network deepening scheme.

result Establishes the first learning rates of underparameterized DCNNs and shows how adding layers can create interpolating DCNNs with good learning rates.

deep convolutional neural networks learning rates underparameterized overparameterized novel network deepening scheme

2022-10-25abs ↗pdf ↗

High-dimensional Black-box Optimization Under Uncertaintymath.OC

New approach optimizes expensive black-box systems with uncertain outputs.

problem Optimizing expensive black-box systems with limited data and uncertainty.

method Flexible non-interpolating surrogate model (TK-MARS) and Smart-Replication approach.

result TK-MARS outperforms original MARS and detects important variables.

black-box optimization uncertainty surrogate modeling replication non-interpolating

2019-11-06abs ↗pdf ↗

Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reductioncs.LG

New algorithms improve SGD convergence and reduce variance for over-parameterized models.

problem Slower convergence in non-interpolation settings for SGD variants.

method Proposed AdaSPS and AdaSLS with variance reduction for robust convergence.

result Achieves faster convergence rates and robustness in non-interpolation settings.

SGD Polyak stepsize Line-search Variance reduction Convergence

2023-08-11abs ↗pdf ↗

Malign Overfitting: Interpolation Can Provably Preclude Invariancecs.LG

Interpolation can prevent classifiers from having desired invariance properties.

problem Invariance properties in over-parameterized models are often ineffective.

method Theoretical analysis and algorithm design for non-interpolating classifiers.

result Interpolating classifiers cannot satisfy desired invariance properties.

overfitting invariance classification fairness robustness

2022-11-28abs ↗pdf ↗

Experimental Design for Overparameterized Learning with Application to Single Shot Deep Active Learningcs.LG

New method for selecting data points in deep learning models.

problem Selecting data points for overparameterized deep learning models.

method Proposes a new experimental design strategy for overparameterized regression and interpolation.

result Demonstrates the effectiveness of the new method in single shot deep active learning.

deep learning experimental design overparameterized models active learning single shot

2020-09-27abs ↗pdf ↗

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimensionstat.ML

New insights into why neural networks can overfit without interpolating data.

problem Understanding why neural networks can overfit without interpolating data in fixed dimensions.

method Analyzing the smoothness of estimators and their derivatives.

result Benign overfitting is possible with estimators that have large enough derivatives, not just in high dimensions but also in fixed dimensions.

benign overfitting neural networks kernel methods neural tangent kernels high-frequency fluctuations

2023-05-23abs ↗pdf ↗

When are ensembles really effective?stat.ML

Ensembling improves performance when classifiers disagree more than average.

problem When do ensembles provide significant performance improvements in classification tasks?

method Theoretical and empirical analysis of ensemble improvement rate and disagreement-error ratio.

result Ensembling improves performance significantly when the disagreement rate is large relative to the average error rate.

ensemble learning classification disagreement-error ratio majority vote competence condition

2023-05-21abs ↗pdf ↗

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizescs.LG

New theory shows large learning rates prevent overfitting in neural networks.

problem Generalization of two-layer ReLU neural networks in noisy regression problems.

method Gradient descent with constant learning rate converges to stable minima.

result Gradient descent with large learning rates finds smooth, sparse fits.

ReLU networks generalization minima stability large step sizes nonparametric regression

2024-06-10abs ↗pdf ↗