SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.18283 · ICML · 2025

Random Feature Representation Boosting

Thomas Cass, Nikita Zozoulenko, Lukas Gonon

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 4 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/2501.18283.json · badge: /api/ran/2501.18283.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
nikitazozoulenko/random-feature-representation-boosting canonical (classifier label)
classifier basis: classifier_2025
5 ran · 4 no recorded run
FunctionStatusWhere it lives
FittableModule Ran
ran on a synthesized input · constructed an object; no result was computed
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("f13f157aeaf67ba5")
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, FittableModule: 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 torch import Tensor

torch.manual_seed(0)

class FittableModule(nn.Module):

    def __init__(self):
        """Base class that wraps nn.Module with a .fit(X, y) 
        and .fit_transform(X, y) method. Requires subclasses to
        implement .forward, as well as either .fit or .fit_transform.
        """
        super(FittableModule, self).__init__()

    def fit(self, X: Tensor, y: Tensor, **kwargs):
        """Fits the model given training data X and targets y.

        Args:
            X (Tensor): Training data, shape (N, D).
            y (Tensor): Training targets, shape (N, d).
        """
        self.fit_transform(X, y)
        return self

    def fit_transform(self, X: Tensor, y: Tensor) -> Tensor:
        """Fit the module and return the transformed data."""
        self.fit(X, y)
        return self(X)


class SimpleFittableModule(FittableModule):
    """Concrete implementation of FittableModule for testing."""
    
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, X: Tensor) -> Tensor:
        return self.linear(X)


X = torch.randn(2, 4)
y = torch.randn(2, 3)

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 FittableModule — 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 FittableModule 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
SWIMLayer Ran
ran on a synthesized input · constructed an object; no result was computed
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("9452a17746aa4396")
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, SWIMLayer: 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

torch.manual_seed(0)

# Define small tensors for training data
# X: (N, D) where N=2 samples, D=4 input dimension
X = torch.randn(2, 4, dtype=torch.float32)

# y: (N, p) where N=2 samples, p=3 output dimension
y = torch.randn(2, 3, dtype=torch.float32)

# Define a simple activation function
activation = nn.Tanh()

# Construct ARGS dictionary with all parameters
ARGS = {
    'in_dim': 4,
    'out_dim': 3,
    'activation': activation,
    'epsilon': 0.01,
    'sampling_method': 'gradient',
    'c': 0.5
}
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 SWIMLayer — 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 SWIMLayer 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
ScaleLayer Ran
ran on a synthesized input · constructed an object; no result was computed
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("c2d5f18425eeec9d")
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, ScaleLayer: 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

torch.manual_seed(0)

ARGS = {
    "scale": 2.5
}
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 ScaleLayer — 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 ScaleLayer 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
create_layer Ran
ran; our contract draft was wrong, not the code
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("7ca2a6661b66eaec")
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 SWIMLayer. 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 torch import Tensor

torch.manual_seed(0)

# Build small tensors for testing
X = torch.randn(2, 4)  # (N=2, D=4) training data
y = torch.randn(2, 3)  # (N=2, p=3) training labels

# Build a simple activation function
activation = nn.Tanh()

# Define the arguments dictionary for create_layer
ARGS = {
    'in_dim': 4,
    'out_dim': 3,
    'layer_type': 'SWIM',
    'iid_scale': 1.0,
    'SWIM_scale': 0.5,
    'activation': activation
}
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 SWIMLayer — a SWIMLayer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SWIMLayer 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
make_fittable Ran
ran; our contract draft was wrong, not the code
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("a03ddcfdcf0c0868")
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 type. 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 torch import Tensor

torch.manual_seed(0)

# Create a simple nn.Module subclass to pass to make_fittable
class SimpleLinearModule(nn.Module):
    def __init__(self, input_dim: int, output_dim: int):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x: Tensor) -> Tensor:
        return self.linear(x)

ARGS = {
    "module_class": SimpleLinearModule
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
BaseGRFRBoost Not yet run
unverified (harvested, no recorded run)
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("6c5456cff2e2a5fe")
How it ran

no invocation recorded.

GhatBoostingLayer Not yet run
unverified (harvested, no recorded run)
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("17fb7c40d07380a6")
How it ran

no invocation recorded.

RandomFeatureLayer Not yet run
unverified (harvested, no recorded run)
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("e5407f0182a3f60b")
How it ran

no invocation recorded.

Upscale Not yet run
unverified (harvested, no recorded run)
nikitazozoulenko/random-feature-representation-boosting/models/random_feature_representation_boosting.py
code served (permissive licence) · get_code("a83fde14f6ef9d33")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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 introduce Random Feature Representation Boosting (RFRBoost), a novel method for constructing deep residual random feature neural networks (RFNNs) using boosting theory. RFRBoost uses random features at each layer to learn the functional gradient of the network representation, enhancing performance while preserving the convex optimization benefits of RFNNs. In the case of MSE loss, we obtain closed-form solutions to greedy layer-wise boosting with random features. For general loss functions, we show that fitting random feature residual blocks reduces to solving a quadratically constrained least squares problem. Through extensive numerical experiments on tabular datasets for both regression and classification, we show that RFRBoost significantly outperforms RFNNs and end-to-end trained MLP ResNets in the small-to medium-scale regime where RFNNs are typically applied. Moreover, RFRBoost offers substantial computational benefits, and theoretical guarantees stemming from boosting theory.

For agents

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

get_harvested_code_for_paper("2501.18283")
get_code_for_paper("2501.18283")
have("2501.18283")

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

curl https://syntology.ai/api/ran/2501.18283.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.18283.svg)](https://syntology.ai/paper/2501.18283)

Connect an agent — have() is free.