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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “Levy-Prokhorov”

Conformal Prediction under Levy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbationsstat.ML

This paper improves conformal prediction for robust interval estimation under distribution shifts.

problem Robustness of conformal prediction under distribution shifts.

method Modeling distribution shifts using Levy-Prokhorov (LP) ambiguity sets, which capture both local and global perturbations.

result Constructs robust conformal prediction intervals that remain valid under distribution shifts.

conformal prediction distribution shifts Levy-Prokhorov robustness interval estimation

2025-02-19abs ↗pdf ↗

Quantitative Error Bounds for Scaling Limits of Stochastic Iterative Algorithmsstat.ML

Derives error bounds for stochastic iterative algorithms using Stein's method.

problem Bounding errors in stochastic iterative algorithms like SGD and SGLD.

method Uses infinite-dimensional Stein's method of exchangeable pairs to derive functional approximation error bounds.

result Establishes non-asymptotic error bounds for algorithm sample paths and variance of iterate averages.

Stein's method stochastic iterative algorithms error bounds Lévy-Prokhorov distance bounded Wasserstein distance

2025-01-21abs ↗pdf ↗

A Compactness Theorem for Embedded Measured Riemann Surface Laminationsmath.GT

We prove a compactness theorem for embedded measured hyperbolic Riemann surface laminations in a compact almost complex manifold $(X, J)$ . To prove compactness result, we show that there is a suitable topology on the space of measured Riemann surface laminations induced by Levy-Prokhorov metric. As an application of th…

2016-10-06abs ↗pdf ↗

Smoothed

f

-Divergence Distributionally Robust Optimizationmath.OC

New optimization method corrects data-driven optimizer's curse.

problem Over-optimistic evaluation in data-driven optimization.

method Smoothed

f

-Divergence Distributionally Robust Optimization (DRO).

result Statistical bound on out-of-sample performance nearly tightest.

optimizer's curse distributionally robust optimization Kullback-Leibler divergence Wasserstein distance statistical bound

2023-06-24abs ↗pdf ↗

Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Datamath.ST

Study on statistical inference for nonlinear stochastic approximation with Markovian data.

problem Statistical inference for nonlinear stochastic approximation algorithms with Markovian data.

method Established a functional central limit theorem for the partial-sum process of the target parameter estimate, providing asymptotic pivotal statistics for constructing confidence intervals.

result Valid and efficient asymptotic inference method for nonlinear stochastic approximation algorithms with Markovian data.

statistical inference nonlinear stochastic approximation Markovian data functional central limit theorem asymptotic pivotal statistic

2023-02-15abs ↗pdf ↗

A New Robust Partial

p

-Wasserstein-Based Metric for Comparing Distributionscs.LG

A new robust metric compares distributions more accurately than existing methods.

problem Sensitivity to outliers and sampling discrepancy in Wasserstein distances.

method Introducing k-RPW, a partial p-Wasserstein distance.

result k-RPW converges faster to true distance and is more robust to outliers.

Wasserstein distance partial p-Wasserstein outlier robustness sampling discrepancy image retrieval

2024-05-06abs ↗pdf ↗

Holistic Robust Data-Driven Decisionsstat.ML

Designs a robust data-driven decision-making model to handle multiple overfitting sources.

problem Overfitting in data-driven models due to statistical error, data noise, and data misspecification.

method Holistic distributionally robust optimization formulation combining Kullback-Leibler and Lévy-Prokhorov approaches.

result Guaranteed holistic protection against statistical error, data noise, and data misspecification.

data-driven decision-making distributionally robust optimization overfitting statistical error data noise

2022-07-19abs ↗pdf ↗