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

3 results for “Hölder-smoothness”

Is Zero-Shot Super-Resolution Possible in Operator Learning?stat.ML

Study shows zero-shot super-resolution in neural operators is impossible in many cases.

problem Understanding the theoretical limits of zero-shot super-resolution in neural operators.

method Systematic theoretical study including information-theoretic and generalization bounds analysis.

result Zero-shot super-resolution is information-theoretically impossible in many settings.

zero-shot super-resolution neural operators operator learning information theory generalization bounds

2026-05-29abs ↗pdf ↗

A Nonparametric Statistics Approach to Feature Selection in Deep Neural Networks with Theoretical Guaranteesstat.ML

This paper selects features in deep neural networks with theoretical guarantees.

problem Feature selection in deep neural networks with unknown nonlinear functions.

method Reformulate neural networks as index models, estimate feature sets using Stein's formula, and apply screening-and-selection mechanism.

result Consistent feature selection with theoretical guarantees, even in high-dimensional settings.

feature selection deep neural networks nonlinear functions Stein's formula screening-and-selection

2025-12-15abs ↗pdf ↗

Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believerscs.LG

New algorithms for interactive learning match minimax bounds efficiently.

problem Interactive learning in the realizable setting with computational efficiency.

method General framework, computationally efficient algorithms, Monte Carlo hit-and-run sampling.

result Sample complexities quantifiable in terms of combinatorial quantities, computationally efficient.

interactive learning realizable setting minimax bounds Monte Carlo hit-and-run

2021-11-09abs ↗pdf ↗