SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.02479 · 2020

A One-bit, Comparison-Based Gradient Estimator

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 0 have no contract verdict; 1 failure of our instrument; 0 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/2010.02479.json · badge: /api/ran/2010.02479.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/SCOBO canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
GetStepSize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
caesarcai/SCOBO/scobo.py
code served (permissive licence) · get_code("9d951750ebfd534b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a simple comparison oracle that returns descent information
class ComparisonOracle:
    def __init__(self):
        self.call_count = 0
    
    def __call__(self, point1, point2):
        """
        Simulates a noisy comparison oracle.
        Returns (is_descend, bit_flipped) tuple.
        is_descend: 1 if point1 is better than point2, 0 otherwise
        bit_flipped: boolean indicating if bit was flipped (not used in function)
        """
        self.call_count += 1
        # Simple heuristic: return descent with high probability initially
        is_descend = 1 if np.random.rand() > 0.3 else 0
        bit_flipped = False
        return (is_descend, bit_flipped)

# Create small tensors for the optimization problem
x = torch.randn(4, 3)  # Current point
g_hat = torch.randn(4, 3)  # Search direction (gradient estimate)
g_hat = g_hat / torch.norm(g_hat)  # Normalize for numerical stability

# Create comparison oracle
comparison_oracle = ComparisonOracle()

# Define step size parameters
last_step_size = 0.1  # Step size from previous iteration
default_step_size = 0.01  # Safe lower bound

# Warm start flag
warm_started = False

ARGS = {
    "Comparison": comparison_oracle,
    "x": x,
    "g_hat": g_hat,
    "last_step_size": last_step_size,
    "default_step_size": default_step_size,
    "warm_started": warm_started
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

We study zeroth-order optimization for convex functions where we further assume that function evaluations are unavailable. Instead, one only has access to a $\textit{comparison oracle}$, which given two points $x$ and $y$ returns a single bit of information indicating which point has larger function value, $f(x)$ or $f(y)$. By treating the gradient as an unknown signal to be recovered, we show how one can use tools from one-bit compressed sensing to construct a robust and reliable estimator of the normalized gradient. We then propose an algorithm, coined SCOBO, that uses this estimator within a gradient descent scheme. We show that when $f(x)$ has some low dimensional structure that can be exploited, SCOBO outperforms the state-of-the-art in terms of query complexity. Our theoretical claims are verified by extensive numerical experiments.

For agents

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

get_harvested_code_for_paper("2010.02479")
get_code_for_paper("2010.02479")
have("2010.02479")

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

curl https://syntology.ai/api/ran/2010.02479.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.02479.svg)](https://syntology.ai/paper/2010.02479)

Connect an agent — have() is free.