SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.06325 · ICLR · 2025

CONGO: COMPRESSIVE ONLINE GRADIENT OPTIMIZATION

Srinivas Shakkottai, Divyanshu Saxena, Aditya Akella, Jeremy Carleton, Prathik Vijaykumar, Dheeraj Narasimha

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2407.06325.json · badge: /api/ran/2407.06325.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
caesarcai/ZORO community
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
BaseOptimizer Ran
ran on a synthesized input
caesarcai/ZORO/optimizers.py
code served (permissive licence) · get_code("d0f772249783b403")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned bool, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import sys

class BaseOptimizer(object):
    """Baseclass with useful methods.

    Inherited by all optimizers."""

    @staticmethod
    def reachedFunctionTarget(function_target, candidate_fitness):
        """Check if fitness is below function_target.

        ... and maybe save some lines of code.
        Args:
                function_target (numeric):
                        Target function value f(y*).
                candidate_fitness (numeric):
                        Function value of the candidate f(c).

        Returns:
                bool: A boolean in indicating if function_target is reached.
        """
        if function_target != None:
            return candidate_fitness <= function_target
        else:
            return False

    @staticmethod
    def reachedFunctionBudget(function_budget, function_evals):
        """Check if maximum number of function evaluations is reached.

        ... and maybe save some lines of code.
        Args:
                function_budget (int):
                        Budget of function evaluations.
                function_evals (int):
                        Function evaluations executed.

        Returns:
                bool: A boolean in indicating if function_budget is reached.
        """
        if function_budget != None:
            return function_evals >= function_budget
        else:
            return False

    @staticmethod
    def report(string_to_print):
        """Report current state.

        Makes a nice user interface.

        **Maybe extend to verbose/non-verbose setting.**

        Args:
                string_to_print (str):
                        String to be printed.
        """
        sys.stdout.write(string_to_print)
        sys.stdout.flush()


INIT_ARGS = {}

ARGS = {
    'function_target': 0.5,
    'candidate_fitness': 0.3,
}

METHOD = 'reachedFunctionTarget'

optimizer = BaseOptimizer(**INIT_ARGS)
result1 = getattr(optimizer, METHOD)(**ARGS)

ARGS2 = {
    'function_budget': 100,
    'function_evals': 50,
}

result2 = optimizer.reachedFunctionBudget(**ARGS2)

ARGS3 = {
    'string_to_print': 'Test message\n',
}

optimizer.report(**ARGS3)

print(f"reachedFunctionTarget result: {result1}")
print(f"reachedFunctionBudget result: {result2}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ZORO Not yet run
unverified (harvested, no recorded run)
caesarcai/ZORO/optimizers.py
code served (permissive licence) · get_code("487e92a67e7a99f3")
How it ran

no invocation recorded.

cosamp Not yet run
unverified (harvested, no recorded run)
caesarcai/ZORO/optimizers.py
code served (permissive licence) · get_code("4dd38d66edeeb9ad")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

FunctionAlso present inEarliest-datedOthers named
BaseOptimizer 1 other paper
1 dated earlier · 1 only as an assembly brick
2102.10707 (2021-02)
A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization

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

We address the challenge of zeroth-order online convex optimization where the objective function's gradient exhibits sparsity, indicating that only a small number of dimensions possess non-zero gradients. Our aim is to leverage this sparsity to obtain useful estimates of the objective function's gradient even when the only information available is a limited number of function samples. Our motivation stems from the optimization of large-scale queueing networks that process timesensitive jobs. Here, a job must be processed by potentially many queues in sequence to produce an output, and the service time at any queue is a function of the resources allocated to that queue. Since resources are costly, the end-to-end latency for jobs must be balanced with the overall cost of the resources used. While the number of queues is substantial, the latency function primarily reacts to resource changes in only a few, rendering the gradient sparse. We tackle this problem by introducing the Compressive Online Gradient Optimization framework which allows compressive sensing methods previously applied to stochastic optimization to achieve regret bounds with an optimal dependence on the time horizon without the full problem dimension appearing in the bound. For specific algorithms, we reduce the samples required per gradient estimate to scale with the gradient's sparsity factor rather than its full dimensionality. Numerical simulations and realworld microservices benchmarks demonstrate CONGO's superiority over gradient descent approaches that do not account for sparsity.

For agents

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

get_harvested_code_for_paper("2407.06325")
get_code_for_paper("2407.06325")
have("2407.06325")

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

curl https://syntology.ai/api/ran/2407.06325.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.06325.svg)](https://syntology.ai/paper/2407.06325)

Connect an agent — have() is free.