SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.02550 · NeurIPS · 2021

CBP: Backpropagation with constraint on weight precision using pseudo-Lagrange multiplier method

Guhyun Kim, Seok Jeong

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 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/2110.02550.json · badge: /api/ran/2110.02550.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
dooseokjeong/cbp canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
constraint Ran
ran on a synthesized input · constructed an object; no result was computed
dooseokjeong/cbp/module.py
code served (permissive licence) · get_code("d3de8bb0f13f3e15")
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 an instance of its own class, constraint: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type 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

torch.manual_seed(0)

# Analyze the function signature and body:
# - weight: tensor, used with detach(), indexing, comparisons
# - scale: tensor, used with detach(), multiplication, comparisons
# - factor: indexable (list/tuple), accessed by [0], [p], [p+1], [-1]
# - b: list, iterable with len(), indexed by [p]
# - ucs: scalar, used in comparisons

# Create small tensors
weight = torch.randn(4, 3)
scale = torch.randn(4, 3)

# factor should be a list with at least len(b) + 1 elements
# Looking at the loop: for p in range(len(b)), we access factor[p], factor[p+1]
# and also factor[0] and factor[-1]
factor = [0.5, 1.0, 1.5, 2.0]

# b should be a list with some elements (len(b) determines loop iterations)
b = [0.7, 1.2]

# ucs is a scalar threshold
ucs = 0.1

ARGS = {
    'weight': weight,
    'scale': scale,
    'factor': factor,
    'b': b,
    'ucs': ucs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type constraint — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a constraint output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
validate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dooseokjeong/cbp/evaluate.py
code served (permissive licence) · get_code("069a320020ac5817")
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) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that satisfies the function's usage
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 10)  # 10 classes for top5 to work
    
    def forward(self, x):
        return self.linear(x)

# Build a minimal data loader
# The function expects data_loader to be iterable, yielding items where:
# - data[0] is a dict with 'data' and 'label' keys
# - data[0]['data'] is a tensor
# - data[0]['label'] is a tensor
# - data_loader has a reset() method

class MinimalDataLoader:
    def __init__(self):
        self.data = [
            (
                {
                    'data': torch.randn(2, 4),      # batch_size=2, input_dim=4
                    'label': torch.randint(0, 10, (2, 1))  # 10 classes
                },
            ),
            (
                {
                    'data': torch.randn(2, 4),
                    'label': torch.randint(0, 10, (2, 1))
                },
            )
        ]
    
    def __iter__(self):
        return iter(self.data)
    
    def reset(self):
        pass

model = MinimalModel()
data_loader = MinimalDataLoader()

ARGS = {
    'model': model,
    'data_loader': data_loader
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Backward propagation of errors (backpropagation) is a method to minimize objective functions (e.g., loss functions) of deep neural networks by identifying optimal sets of weights and biases. Imposing constraints on weight precision is often required to alleviate prohibitive workloads on hardware. Despite the remarkable success of backpropagation, the algorithm itself is not capable of considering such constraints unless additional algorithms are applied simultaneously. To address this issue, we propose the constrained backpropagation (CBP) algorithm based on the pseudo-Lagrange multiplier method to obtain the optimal set of weights that satisfy a given set of constraints. The defining characteristic of the proposed CBP algorithm is the utilization of a Lagrangian function (loss function plus constraint function) as its objective function. We considered various types of constraints -binary, ternary, one-bit shift, and two-bit shift weight constraints. As a posttraining method, CBP applied to AlexNet, ResNet-18, ResNet-50, and GoogLeNet on ImageNet, which were pre-trained using the conventional backpropagation. For most cases, the proposed algorithm outperforms the state-of-the-art methods on ImageNet, e.g., 66.6%, 74.4%, and 64.0% top-1 accuracy for ResNet-18, ResNet-50, and GoogLeNet with binary weights, respectively. This highlights CBP as a learning algorithm to address diverse constraints with the minimal performance loss by employing appropriate constraint functions. The code for CBP is publicly available at https://github.com/dooseokjeong/CBP.

For agents

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

get_harvested_code_for_paper("2110.02550")
get_code_for_paper("2110.02550")
have("2110.02550")

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

curl https://syntology.ai/api/ran/2110.02550.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.02550.svg)](https://syntology.ai/paper/2110.02550)

Connect an agent — have() is free.