SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.08111 · ICML · 2022

On Private Online Convex Optimization: Optimal Algorithms in p -Geometry and High Dimensional Contextual Bandits

Yuxuan Han, Zhicong Liang, Zhipeng Liang, Yang Wang, Yuan Yao, Jiheng Zhang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2206.08111.json · badge: /api/ran/2206.08111.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
liangzp/dp-streaming-sco canonical (classifier label)
classifier basis: classifier_2025
4 ran · 3 no recorded run
FunctionStatusWhere it lives
GGPlus Ran
ran, honoured the contract we drafted
liangzp/dp-streaming-sco/algo.py
pointer only (licence: NONE) · get_code("b28a1d672db2c066")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzp/dp-streaming-sco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

argmin Ran
ran, violated the contract we drafted
liangzp/dp-streaming-sco/algo.py
pointer only (licence: NONE) · get_code("b0058a9541adde62")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzp/dp-streaming-sco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

clip Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liangzp/dp-streaming-sco/algo.py
pointer only (licence: NONE) · get_code("6a5aa4ef50c866cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzp/dp-streaming-sco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_linear_gradient Ran
ran, honoured the contract we drafted
liangzp/dp-streaming-sco/algo.py
pointer only (licence: NONE) · get_code("c89e3ebfc5f170f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzp/dp-streaming-sco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Algo Not yet run
unverified (harvested, no recorded run)
liangzp/dp-streaming-sco/algo.py
pointer only (licence: NONE) · get_code("e7cf6e54ab093727")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzp/dp-streaming-sco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

OFW_ple2 Not yet run
unverified (harvested, no recorded run)
liangzp/dp-streaming-sco/algo.py
pointer only (licence: NONE) · get_code("15252effeb43a9af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzp/dp-streaming-sco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

paras Not yet run
unverified (harvested, no recorded run)
liangzp/dp-streaming-sco/algo.py
pointer only (licence: NONE) · get_code("47f521b2924b61d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liangzp/dp-streaming-sco when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Differentially private (DP) stochastic convex optimization (SCO) is ubiquitous in trustworthy machine learning algorithm design. This paper studies the DP-SCO problem with streaming data sampled from a distribution and arrives sequentially. We also consider the continual release model where parameters related to private information are updated and released upon each new data, often known as the online algorithms. Despite that numerous algorithms have been developed to achieve the optimal excess risks in different p norm geometries, yet none of the existing ones can be adapted to the streaming and continual release setting. To address such a challenge as the online convex optimization with privacy protection, we propose a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction to update and reveal the parameters upon each data. Combined with the adaptive differential privacy analysis, our online algorithm achieves in linear time the optimal excess risk when 1 < p ≤ 2 and the state-of-the-art excess risk meeting the non-private lower ones when 2 < p ≤ ∞. Our algorithm can also be extended to the case p = 1 to achieve nearly dimension-independent excess risk. While previous variance reduction results on recursive gradient have theoretical guarantee only in the independent and identically distributed sample setting, we establish such a guarantee in a non-stationary setting. To demonstrate the virtues of our method, we design the first DP algorithm for high-dimensional generalized linear bandits with logarithmic regret. Comparative experiments with a variety of DP-SCO and DP-Bandit algorithms exhibit the efficacy and utility of the proposed algorithms.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.08111")
get_code_for_paper("2206.08111")
have("2206.08111")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2206.08111.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2206.08111.svg)](https://syntology.ai/paper/2206.08111)

Connect an agent — have() is free.