SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.09191 · NeurIPS · 2020

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining

José Hernández-Lobato, Austin Tripp, Erik Daxberger

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 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; 2 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/2006.09191.json · badge: /api/ran/2006.09191.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
cambridge-mlg/weighted-retraining canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 1 no recorded run
mkusner/grammarVAE community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
gp_performance_metrics Ran
ran on a synthesized input
cambridge-mlg/weighted-retraining/weighted_retraining/gp_train.py
code served (permissive licence) · get_code("965c6ca9f6bdf6cb")
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 dict. 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 numpy as np
import tensorflow as tf

torch.manual_seed(0)

class MockGP:
    """Mock Gaussian Process model with required methods"""
    def __init__(self):
        self._training_loss_value = tf.constant(0.5)
    
    def training_loss(self):
        """Return training loss as a tensor"""
        return self._training_loss_value
    
    def predict_f(self, x):
        """Predict mean and variance"""
        batch_size = x.shape[0]
        mu = tf.constant(np.random.randn(batch_size, 1), dtype=tf.float32)
        var = tf.constant(np.ones((batch_size, 1)), dtype=tf.float32)
        return mu, var
    
    def predict_log_density(self, data):
        """Predict log density for given data"""
        x, y = data
        batch_size = x.shape[0]
        log_pdf = tf.constant(np.random.randn(batch_size), dtype=tf.float32)
        return log_pdf

# Create mock GP instance
gp = MockGP()

# Create datasets - each is a tuple of (x, y)
# x shape: (batch_size, input_dim), y shape: (batch_size, output_dim)
x_train = tf.constant(np.random.randn(2, 4).astype(np.float32))
y_train = np.random.randn(2, 1).astype(np.float32)

x_test = tf.constant(np.random.randn(2, 4).astype(np.float32))
y_test = np.random.randn(2, 1).astype(np.float32)

datasets = [
    (x_train, y_train),
    (x_test, y_test)
]

dataset_names = ["train", "test"]

ARGS = {
    "gp": gp,
    "datasets": datasets,
    "dataset_names": dataset_names
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
pop_or_nothing Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from mkusner/grammarVAE
pointer only; the stored copy get_code serves, from mkusner/grammarVAE, is pointer only (licence: NONE) · get_code("16eaf789c4a4401d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

prods_to_eq Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from mkusner/grammarVAE
pointer only; the stored copy get_code serves, from mkusner/grammarVAE, is pointer only (licence: NONE) · get_code("0bf41e0b28d9835c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

ZincGrammarModel Not yet run
unverified (harvested, no recorded run)
mkusner/grammarVAE/molecule_vae.py
pointer only (licence: NONE) · get_code("cb40f0c69ca29671")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mkusner/grammarVAE 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.

get_zinc_tokenizer Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from mkusner/grammarVAE
pointer only; the stored copy get_code serves, from mkusner/grammarVAE, is pointer only (licence: NONE) · get_code("bd5df031b64e57d3")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

robust_multi_restart_optimizer Not yet run
unverified (harvested, no recorded run)
cambridge-mlg/weighted-retraining/weighted_retraining/gp_opt.py
code served (permissive licence) · get_code("b30f075b7653c03d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 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.

FunctionAlso present inEarliest-datedOthers named
get_zinc_tokenizer
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1703.01925 (2017-03)
Grammar Variational Autoencoder
pop_or_nothing
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1703.01925 (2017-03)
Grammar Variational Autoencoder
prods_to_eq
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1703.01925 (2017-03)
Grammar Variational Autoencoder

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

Many important problems in science and engineering, such as drug design, involve optimizing an expensive black-box objective function over a complex, highdimensional, and structured input space. Although machine learning techniques have shown promise in solving such problems, existing approaches substantially lack sample efficiency. We introduce an improved method for efficient black-box optimization, which performs the optimization in the low-dimensional, continuous latent manifold learned by a deep generative model. In contrast to previous approaches, we actively steer the generative model to maintain a latent manifold that is highly useful for efficiently optimizing the objective. We achieve this by periodically retraining the generative model on the data points queried along the optimization trajectory, as well as weighting those data points according to their objective function value. This weighted retraining can be easily implemented on top of existing methods, and is empirically shown to significantly improve their efficiency and performance on synthetic and real-world optimization problems.

For agents

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

get_harvested_code_for_paper("2006.09191")
get_code_for_paper("2006.09191")
have("2006.09191")

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

curl https://syntology.ai/api/ran/2006.09191.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.09191.svg)](https://syntology.ai/paper/2006.09191)

Connect an agent — have() is free.