SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.02798 · ICML · 2020

How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization

Chris Finlay, Jörn-Henrik Jacobsen, Levon Nurbekyan, Adam Oberman

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 4 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2002.02798.json · badge: /api/ran/2002.02798.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
D-hash-code/ffjord-rnode-finalweek-mnist community (classifier label)
classifier basis not recorded on the link
11 ran · 3 no recorded run
cfinlay/ffjord-rnode community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
RegularizedODEfunc Ran
ran on a synthesized input · constructed an object; no result was computed
cfinlay/ffjord-rnode/lib/layers/wrappers/cnf_regularization.py
code served (permissive licence) · get_code("2a06912ee47c2847")
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, RegularizedODEfunc: 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)

# Create a minimal ODEFunc that the RegularizedODEfunc wraps
class MinimalODEFunc(nn.Module):
    def __init__(self):
        super(MinimalODEFunc, self).__init__()
        self._num_evals = 0
    
    def before_odeint(self, *args, **kwargs):
        pass
    
    def forward(self, t, state):
        # state is (x, logp)
        x, logp = state
        # Return (dx, dlogp)
        dx = torch.zeros_like(x)
        dlogp = torch.zeros_like(logp)
        return (dx, dlogp)

# Create minimal regularization functions
def regularization_fn_1(x, t, logp, dx, dlogp, odefunc):
    # Returns a tuple representing regularization contribution
    return torch.zeros_like(dx)

def regularization_fn_2(x, t, logp, dx, dlogp, odefunc):
    # Returns a tuple representing regularization contribution
    return torch.zeros_like(dlogp)

# Create the odefunc instance
odefunc = MinimalODEFunc()

# Create list of regularization functions
regularization_fns = [regularization_fn_1, regularization_fn_2]

ARGS = {
    'odefunc': odefunc,
    'regularization_fns': regularization_fns,
}
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 RegularizedODEfunc — 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 RegularizedODEfunc 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
build_net Ran
ran on a synthesized input
D-hash-code/ffjord-rnode-finalweek-mnist/lib/layers/coupling.py
code served (permissive licence) · get_code("1bfb103fe91e335d")
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 Sequential. 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 = {
    'input_dim': 4,
    'hidden_dims': [8, 6],
    'activation': 'relu'
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
count_parameters Ran
ran, honoured the contract we drafted
D-hash-code/ffjord-rnode-finalweek-mnist/train_misc.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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 int, ndim 0, dtype family int, 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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
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 int, ndim 0, dtype family int, 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
get_logger Ran
ran; our contract draft was wrong, not the code
D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils.py
code served (permissive licence) · get_code("416b44e8cb9fc048")
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 RootLogger. 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 logging
import tempfile
import os

# Create temporary files for the function to read
temp_dir = tempfile.mkdtemp()
logpath = os.path.join(temp_dir, "test.log")
filepath = os.path.join(temp_dir, "main_script.py")
package_file_1 = os.path.join(temp_dir, "package_1.py")
package_file_2 = os.path.join(temp_dir, "package_2.py")

# Write content to the files
with open(filepath, 'w') as f:
    f.write("# Main script content\nprint('hello')\n")

with open(package_file_1, 'w') as f:
    f.write("# Package 1 content\ndef func1(): pass\n")

with open(package_file_2, 'w') as f:
    f.write("# Package 2 content\ndef func2(): pass\n")

ARGS = {
    'logpath': logpath,
    'filepath': filepath,
    'package_files': [package_file_1, package_file_2],
    'displaying': True,
    'saving': True,
    'debug': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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
isnan Ran
ran on a synthesized input
D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils.py
code served (permissive licence) · get_code("005ab5343cd3459c")
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 Tensor, ndim 1, dtype family float, shape (4,) 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 torch

torch.manual_seed(0)

# The function isnan(tensor) checks if tensor != tensor
# This works on torch tensors and returns a boolean tensor
# We need to pass a tensor that supports the != operator

tensor = torch.tensor([1.0, float('nan'), 3.0, 4.0])

ARGS = {
    "tensor": tensor
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
logsumexp Ran
ran; our contract draft was wrong, not the code
D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils.py
code served (permissive licence) · get_code("bc02f37ed2da5d95")
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 Tensor, ndim 1, dtype family float, shape (2,) 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 torch
import math
from numbers import Number

torch.manual_seed(0)

# Test case 1: 2D tensor with dim specified
value_2d = torch.randn(2, 4)
dim_arg = 1
keepdim_arg = False

ARGS = {
    "value": value_2d,
    "dim": dim_arg,
    "keepdim": keepdim_arg,
}
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 Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
reduce_tensor Ran
ran; our contract draft was wrong, not the code
D-hash-code/ffjord-rnode-finalweek-mnist/dist_utils.py
code served (permissive licence) · get_code("be51985b302891b6")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch
import torch.distributed as dist
import os

# Set up minimal distributed environment simulation
os.environ['WORLD_SIZE'] = '2'
os.environ['RANK'] = '0'
os.environ['MASTER_ADDR'] = 'localhost'
os.environ['MASTER_PORT'] = '29500'

# Initialize torch distributed (this will fail in non-distributed context,
# so we'll mock the dist module instead)
torch.manual_seed(0)

# Create a mock distributed module since we're in a single-process environment
class MockReduceOp:
    SUM = 0

class MockDist:
    ReduceOp = MockReduceOp()
    
    @staticmethod
    def all_reduce(tensor, op=None):
        # In a real distributed setting, this would sum across processes
        # For testing, we just scale by world size to simulate summing across 2 processes
        tensor.mul_(2)
        return None

# Monkey-patch dist for this test
original_dist = dist
dist.all_reduce = MockDist.all_reduce
dist.ReduceOp = MockDist.ReduceOp

# Create a small test tensor
test_tensor = torch.randn(2, 4)

ARGS = {
    'tensor': test_tensor
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
sample_mask Ran
ran on a synthesized input
D-hash-code/ffjord-rnode-finalweek-mnist/lib/layers/coupling.py
code served (permissive licence) · get_code("3a7bef4c55086f50")
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 Tensor, ndim 1, dtype family float, shape (8,) 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 torch

torch.manual_seed(0)

ARGS = {
    'dim': 8,
    'mask_type': 'alternate',
    'swap': False
}
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 Tensor, ndim 1, dtype family float, shape (8,) — shape (8,) 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
shift Ran
ran on a synthesized input
D-hash-code/ffjord-rnode-finalweek-mnist/trainCNFGAN.py
code served (permissive licence) · get_code("eff72070f790a5fe")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# Create a small tensor to pass to the shift function
# The function expects x to have methods: add_, div_
# These are tensor methods, so x should be a tensor
x = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                   [5.0, 6.0, 7.0, 8.0]], dtype=torch.float32)

# nbits parameter - an integer controlling the bit shift
nbits = 8

ARGS = {
    "x": x,
    "nbits": nbits
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
standard_normal_logprob Ran
ran; our contract draft was wrong, not the code
D-hash-code/ffjord-rnode-finalweek-mnist/train_misc.py
code served (permissive licence) · get_code("2dc23e3f121c6a38")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch
import math

torch.manual_seed(0)

# The function expects a tensor z with a pow method and supports element-wise operations
z = torch.randn(2, 4)

ARGS = {
    "z": z
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
sum_tensor Ran
ran on a synthesized input
D-hash-code/ffjord-rnode-finalweek-mnist/dist_utils.py
code served (permissive licence) · get_code("0009ce40d4f5ff19")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch
import torch.distributed as dist

torch.manual_seed(0)

# Initialize the default process group for distributed operations
# This is required for dist.all_reduce to work
if not dist.is_available():
    raise RuntimeError("torch.distributed is not available")

# For CPU-only testing, we need to initialize the process group
# Using the 'gloo' backend which works on CPU
try:
    dist.init_process_group(backend='gloo', init_method='tcp://127.0.0.1:29500', rank=0, world_size=1)
except RuntimeError:
    # If already initialized, that's fine
    pass

# Create a small tensor as input
tensor = torch.randn(2, 4)

ARGS = {
    'tensor': tensor
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
unshift Ran
ran on a synthesized input
D-hash-code/ffjord-rnode-finalweek-mnist/trainCNFGAN.py
code served (permissive licence) · get_code("4df0e0f1164421a1")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# The function unshift takes a tensor x and an optional nbits parameter
# It calls x.add_() which is an in-place add operation on a tensor
# So x must be a torch.Tensor

x = torch.randn(2, 4)
nbits = 8

ARGS = {
    "x": x,
    "nbits": nbits,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
add_noise Not yet run
unverified (harvested, no recorded run)
D-hash-code/ffjord-rnode-finalweek-mnist/trainCNFGAN.py
code served (permissive licence) · get_code("13a2192e17a601cb")
How it ran

no invocation recorded.

add_noise Not yet run
unverified (harvested, no recorded run)
D-hash-code/ffjord-rnode-finalweek-mnist/validate.py
code served (permissive licence) · get_code("6e49bcc681db6ead")
How it ran

no invocation recorded.

get_data_loader Not yet run
unverified (harvested, no recorded run)
D-hash-code/ffjord-rnode-finalweek-mnist/lib/utils2.py
code served (permissive licence) · get_code("58bb14039809fdf3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
count_parameters 180 other papers
16 dated earlier, 164 later · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
standard_normal_logprob 7 other papers
2 dated earlier, 5 later
1811.00995 (2018-11)
Invertible Residual Networks
1906.02735 (2019-06)
Residual Flows for Invertible Generative Modeling
2012.05942 (2020-12)
Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
and 4 more not named here
get_logger 5 other papers
2 dated earlier, 3 later
1906.02735 (2019-06)
Residual Flows for Invertible Generative Modeling
1911.07532 (2019-11)
Graph Neural Ordinary Differential Equations
2110.00527 (2021-10)
Consistent Explanations by Contrastive Learning
and 2 more not named here
logsumexp 5 other papers
4 dated earlier, 1 later
1710.11417 (2017-10)
TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
1802.04942 (2018-02)
Isolating Sources of Disentanglement in Variational Autoencoders
1809.10341 (2018-09)
Deep Graph Infomax
and 2 more not named here
isnan 2 other papers
2 dated earlier
1802.04942 (2018-02)
Isolating Sources of Disentanglement in Variational Autoencoders
1906.02735 (2019-06)
Residual Flows for Invertible Generative Modeling
reduce_tensor 1 other paper
1 dated earlier
1905.11468 (2019-05)
Scaleable input gradient regularization for adversarial robustness

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Training neural ODEs on large datasets has not been tractable due to the necessity of allowing the adaptive numerical ODE solver to refine its step size to very small values. In practice this leads to dynamics equivalent to many hundreds or even thousands of layers. In this paper, we overcome this apparent difficulty by introducing a theoretically-grounded combination of both optimal transport and stability regularizations which encourage neural ODEs to prefer simpler dynamics out of all the dynamics that solve a problem well. Simpler dynamics lead to faster convergence and to fewer discretizations of the solver, considerably decreasing wall-clock time without loss in performance. Our approach allows us to train neural ODE-based generative models to the same performance as the unregularized dynamics, with significant reductions in training time. This brings neural ODEs closer to practical relevance in large-scale applications.

For agents

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

get_harvested_code_for_paper("2002.02798")
get_code_for_paper("2002.02798")
have("2002.02798")

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

curl https://syntology.ai/api/ran/2002.02798.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.02798.svg)](https://syntology.ai/paper/2002.02798)

Connect an agent — have() is free.