SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.01212 · ICML · 2022

spred: Solving L 1 Penalty with SGD

Liu Ziyin, Zihao Wang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 2 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/2210.01212.json · badge: /api/ran/2210.01212.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
zihao-wang/spred canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
zihao-wang/sparsity-by-redundancy marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
MyModelMixin Ran
ran on a synthesized input · constructed an object; no result was computed
zihao-wang/sparsity-by-redundancy/non-linear/models.py
code served (permissive licence) · get_code("b5bcfe01b5f45a60")
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, MyModelMixin: the run constructed the object and did not call it, so no result was computed. The image it ran in was 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
import torch.nn as nn
from typing import Dict

torch.manual_seed(0)

class ConcreteModel(nn.Module, object):
    """Concrete implementation of MyModelMixin"""
    
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def get_weights(self) -> Dict:
        """Returns a dictionary of model weights"""
        weights_dict = {}
        for name, param in self.named_parameters():
            weights_dict[name] = param.data.clone()
        return weights_dict
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model_instance = ConcreteModel()

ARGS = {}
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 MyModelMixin — 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 MyModelMixin 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
SpaRedLinear Ran
ran on a synthesized input
zihao-wang/sparsity-by-redundancy/non-linear/models.py
code served (permissive licence) · get_code("e405bc363658ed80")
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 Tensor, ndim 2, 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
from torch import nn
import math

class MyModelMixin:
    def get_weights(self):
        pass

class SpaRedLinear(nn.Module, MyModelMixin):

    def __init__(self, in_features: int, out_features: int, bias: bool=False, device=None, dtype=None) -> None:
        factory_kwargs = {'device': device, 'dtype': dtype}
        super(SpaRedLinear, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.weight = nn.Parameter(torch.empty((out_features, in_features), **factory_kwargs))
        self.weight2 = nn.Parameter(torch.empty((out_features, in_features), **factory_kwargs))
        self.use_bias = bias
        if bias:
            self.bias = nn.Parameter(torch.empty(out_features, **factory_kwargs))
            self.bias2 = nn.Parameter(torch.empty(out_features, **factory_kwargs))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self) -> None:
        from torch.nn import init
        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        init.kaiming_uniform_(self.weight2, a=math.sqrt(5))
        if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in) if fan_in > 0 else 0
            init.uniform_(self.bias, -bound, bound)
            init.uniform_(self.bias2, -bound, bound)

    def forward(self, X, **kwargs):
        weight = self.weight * self.weight2
        if self.use_bias:
            bias = self.bias * self.bias2
            x = nn.functional.linear(X, weight, bias)
        else:
            x = nn.functional.linear(X, weight)
        assert not torch.isnan(x).any()
        return x

    def get_weights(self):
        if self.use_bias:
            return {'weight': self.weight * self.weight2, 'bias': self.bias * self.bias2}
        else:
            return {'weight': self.weight * self.weight2}


INIT_ARGS = {
    'in_features': 4,
    'out_features': 3,
    'bias': True,
    'device': None,
    'dtype': None
}

ARGS = {
    'X': torch.randn(2, 4)
}

if __name__ == '__main__':
    model = SpaRedLinear(**INIT_ARGS)
    output = model(**ARGS)
    print("Output shape:", output.shape)
    print("Output:", output)
    weights = model.get_weights()
    print("Weights keys:", weights.keys())
    print("Weight shape:", weights['weight'].shape)
    print("Bias shape:", weights['bias'].shape)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, 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)
get_closest_alpha Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zihao-wang/spred/linear/high_dim_regression.py
code served (permissive licence) · get_code("dc646d05e35482d6")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# Construct arguments for get_closest_alpha
alphas = [0.1, 0.5, 0.9, 1.5, 2.0]
a = 0.7

ARGS = {
    "alphas": alphas,
    "a": a,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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 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, 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 3 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 propose to minimize a generic differentiable objective with L 1 constraint using a simple reparametrization and straightforward stochastic gradient descent. Our proposal is the direct generalization of previous ideas that the L 1 penalty may be equivalent to a differentiable reparametrization with weight decay. We prove that the proposed method, spred, is an exact differentiable solver of L 1 and that the reparametrization trick is completely "benign" for a generic nonconvex function. Practically, we demonstrate the usefulness of the method in ( 1) training sparse neural networks to perform gene selection tasks, which involves finding relevant features in a very high dimensional space, and (2) neural network compression task, to which previous attempts at applying the L 1penalty have been unsuccessful. Conceptually, our result bridges the gap between the sparsity in deep learning and conventional statistical learning.

For agents

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

get_harvested_code_for_paper("2210.01212")
get_code_for_paper("2210.01212")
have("2210.01212")

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

curl https://syntology.ai/api/ran/2210.01212.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.01212.svg)](https://syntology.ai/paper/2210.01212)

Connect an agent — have() is free.