Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
Authors: Bo Li, Wei Wang, Peng Ye
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this work, we present a new algorithm with a mistake bound of O(d log T) against an adaptive adversary, closing this gap. We further investigate the problem in the agnostic setting, which is more general than the realizable setting as it does not impose any assumptions on the data. We give an algorithm that obtains a sublinear regret of O( d T) for generic Littlestone classes, demonstrating that they are also privately online learnable in the agnostic setting. |
| Researcher Affiliation | Academia | 1Guangzhou HKUST Fok Ying Tung Research Institute 2Department of Computer Science and Engineering, HKUST EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1: Update Algorithm 2: Realizable learner Algorithm 3: A simple private online learner Algorithm 4: Agnostic empirical learner Algorithm 5: Sanitization for intervals Algorithm 6: Expert Algorithm 7: Constructing experts |
| Open Source Code | No | The paper does not include experiments requiring code. |
| Open Datasets | No | The paper does not include experiments. |
| Dataset Splits | No | The paper does not include experiments. |
| Hardware Specification | No | The paper does not include experiments. |
| Software Dependencies | No | The paper does not include experiments. |
| Experiment Setup | No | The paper does not include experiments. |