SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.01798 · NeurIPS · 2021

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

Pasquale Minervini, Mathias Niepert, Luca Franceschi

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 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; 5 failures of our instrument; 3 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2106.01798.json · badge: /api/ran/2106.01798.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
nec-research/tf-imle canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
uclnlp/torch-imle reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
SerChirag/rs-imle extension (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
draw_gaussian_diag_samples Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SerChirag/rs-imle/helpers/imle_helpers.py
pointer only (licence: NONE) · get_code("aac686caa4fc5236")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SerChirag/rs-imle when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TargetDistribution Ran
ran on a synthesized input · constructed an object; no result was computed
uclnlp/torch-imle/imle/wrapper.py
code served (permissive licence) · get_code("63886bbe7b1f023d")
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, TargetDistribution: 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

torch.manual_seed(0)

ARGS = {
    "alpha": 1.0,
    "beta": 1.0,
}
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 TargetDistribution — 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 TargetDistribution 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
_IMLE_PID Ran
ran on a synthesized input · constructed an object; no result was computed
nec-research/tf-imle/SYNTH/imle.py
pointer only (licence: NOASSERTION) · get_code("518265639d392d1a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, nec-research/tf-imle (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_maybe_ctx_call Ran
ran; our contract draft was wrong, not the code
nec-research/tf-imle/SYNTH/imle.py
pointer only (licence: NOASSERTION) · get_code("a6163b5a095df556")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, nec-research/tf-imle (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gaussian_analytical_kl Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SerChirag/rs-imle/helpers/imle_helpers.py
pointer only (licence: NONE) · get_code("f8752a89ed52495c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SerChirag/rs-imle when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

imle Ran
ran; our contract draft was wrong, not the code
uclnlp/torch-imle/imle/wrapper.py
code served (permissive licence) · get_code("728c8123b133d083")
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 function. 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, Size
from abc import ABC, abstractmethod

torch.manual_seed(0)

# Define a minimal noise distribution
class SimpleNoiseDistribution(ABC):
    def __init__(self):
        super().__init__()
    
    def sample(self, shape: Size) -> Tensor:
        return torch.randn(shape)

# Define a minimal target distribution
class SimpleTargetDistribution(ABC):
    def __init__(self):
        super().__init__()
    
    def params(self, theta: Tensor, dy: Tensor) -> Tensor:
        return theta - dy

# Define a simple black-box solver function
def simple_solver(weights_batch: Tensor) -> Tensor:
    """A minimal black-box combinatorial solver that returns a solution."""
    # Return a simple solution based on input
    return torch.round(torch.sigmoid(weights_batch))

# Create instances
noise_dist = SimpleNoiseDistribution()
target_dist = SimpleTargetDistribution()

ARGS = {
    "function": simple_solver,
    "target_distribution": target_dist,
    "noise_distribution": noise_dist,
    "nb_samples": 2,
    "input_noise_temperature": 1.0,
    "target_noise_temperature": 1.0,
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
imle_pid Ran
ran; our contract draft was wrong, not the code
nec-research/tf-imle/SYNTH/imle.py
pointer only (licence: NOASSERTION) · get_code("b781568015623ad1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, nec-research/tf-imle (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BaseNoiseDistribution Not yet run
unverified (harvested, no recorded run)
uclnlp/torch-imle/imle/wrapper.py
code served (permissive licence) · get_code("8c92b1b7ad6eec54")
How it ran

no invocation recorded.

BaseTargetDistribution Not yet run
unverified (harvested, no recorded run)
uclnlp/torch-imle/imle/wrapper.py
code served (permissive licence) · get_code("cb1a5474e20e34cf")
How it ran

no invocation recorded.

get_conv Not yet run
unverified (harvested, no recorded run)
SerChirag/rs-imle/helpers/imle_helpers.py
pointer only (licence: NONE) · get_code("52eba97aab7c3b34")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SerChirag/rs-imle when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
gaussian_analytical_kl 1 other paper
1 dated earlier
2011.10650 (2020-11)
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images

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

Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components. I-MLE is widely applicable as it only requires the ability to compute the most probable states and does not rely on smooth relaxations. The framework encompasses several approaches such as perturbation-based implicit differentiation and recent methods to differentiate through black-box combinatorial solvers. We introduce a novel class of noise distributions for approximating marginals via perturb-and-MAP. Moreover, we show that I-MLE simplifies to maximum likelihood estimation when used in some recently studied learning settings that involve combinatorial solvers. Experiments on several datasets suggest that I-MLE is competitive with and often outperforms existing approaches which rely on problem-specific relaxations.

For agents

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

get_harvested_code_for_paper("2106.01798")
get_code_for_paper("2106.01798")
have("2106.01798")

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

curl https://syntology.ai/api/ran/2106.01798.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.01798.svg)](https://syntology.ai/paper/2106.01798)

Connect an agent — have() is free.