paper-with-me

홈 › Papers

Private Prediction via Shrinkage

2026-02-05 · Chao Yan arxiv

We study differentially private prediction introduced by Dwork and Feldman (COLT 2018): an algorithm receives one labeled sample set $S$ and then answers a stream of unlabeled queries while the output transcript remains $(\varepsilon,δ)$-differentially private with respect to $S$. Standard composition yields a $\sqrt{T}$ dependence for $T$ queries. We show that this dependence can be reduced to polylogarithmic in $T$ in streaming settings. For an oblivious online adversary and any concept class $\mathcal{C}$, we give a private predictor that answers $T$ queries with $|S|= \tilde{O}(VC(\mathcal{C})^{3.5}\log^{3.5}T)$ labeled examples. For an adaptive online adversary and halfspaces over $\mathbb{R}^d$, we obtain $|S|=\tilde{O}\left(d^{5.5}\log T\right)$.

📄 PDF Abstract BibTeX arXiv:2602.05219

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Noise-Aware Shrinkage for Differentially Private Zeroth-Order Fine-Tuning of Large Language Models

2026-08-04 · Lele Zheng, Weifeng Kong, Xinyi Zhang, Ke Cheng 외 arxiv

Differentially private zeroth-order optimization (DP-ZO) enables memory-efficient private fine-tuning of large language models using only forward evaluations. Existing aggregation-based DP-ZO methods reconstruct model up…

Prediction-Powered Adaptive Shrinkage Estimation

2025-02-20 · Sida Li, Nikolaos Ignatiadis

Prediction-Powered Inference (PPI) is a powerful framework for enhancing statistical estimates by combining limited gold-standard data with machine learning (ML) predictions. While prior work has demonstrated PPI's benef…

Prediction

Hierarchical Modeling and Shrinkage for User Session Length Prediction in Media Streaming

2018-03-04 · Antoine Dedieu, Rahul Mazumder, Zhen Zhu, Hossein Vahabi

An important metric of users' satisfaction and engagement within on-line streaming services is the user session length, i.e. the amount of time they spend on a service continuously without interruption. Being able to pre…

Guiding adaptive shrinkage by co-data to improve regression-based prediction and feature selection

2024-05-08 · Mark A. van de Wiel, Wessel N. van Wieringen

The high dimensional nature of genomics data complicates feature selection, in particular in low sample size studies - not uncommon in clinical prediction settings. It is widely recognized that complementary data on the …

feature selection

Auto-Regressive U-Net for Full-Field Prediction of Shrinkage-Induced Damage in Concrete

2025-09-24 · Liya Gaynutdinova, Petr Havlásek, Ondřej Rokoš, Fleur Hendriks 외 arxiv

This paper introduces a deep learning approach for predicting time-dependent full-field damage in concrete. The study uses an auto-regressive U-Net model to predict the evolution of the scalar damage field in a unit cell…

Computational Efficiency