SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.11872 · 2022

Local Latent Space Bayesian Optimization over Structured Inputs

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
nataliemaus/lolbo canonical 4 of 9
FunctionStatusWhere it lives
compute_train_zs Ran nataliemaus/lolbo/lolbo/utils/mol_utils/load_data.py
code served (permissive licence) · get_code("73e65b4bd30bbd77")
gumbel_softmax Ran nataliemaus/lolbo/lolbo/utils/mol_utils/selfies_vae/model_positional_unbounded.py
code served (permissive licence) · get_code("5b05e8e843deabaf")
is_valid_molecule Ran nataliemaus/lolbo/lolbo/utils/mol_utils/selfies_vae/model_positional_unbounded.py
code served (permissive licence) · get_code("f8e7af52c159f99d")
load_molecule_train_data Ran nataliemaus/lolbo/lolbo/utils/mol_utils/load_data.py
code served (permissive licence) · get_code("8e738b81f68971d1")
generate_batch Not yet run nataliemaus/lolbo/lolbo/utils/bo_utils/turbo.py
code served (permissive licence) · get_code("de6ce50bd4f3d1ca")
load_train_z Not yet run nataliemaus/lolbo/lolbo/utils/mol_utils/load_data.py
code served (permissive licence) · get_code("e00ccb61913dc9fb")
update_models_end_to_end Not yet run nataliemaus/lolbo/lolbo/utils/utils.py
code served (permissive licence) · get_code("d3895f341b61aad6")
update_state Not yet run nataliemaus/lolbo/lolbo/utils/bo_utils/turbo.py
code served (permissive licence) · get_code("ba51f9dac22959af")
update_surr_model Not yet run nataliemaus/lolbo/lolbo/utils/utils.py
code served (permissive licence) · get_code("0dda692b10a19709")

Repositories linked to this paper

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

Abstract

Bayesian optimization over the latent spaces of deep autoencoder models (DAEs) has recently emerged as a promising new approach for optimizing challenging black-box functions over structured, discrete, hard-to-enumerate search spaces (e.g., molecules). Here the DAE dramatically simplifies the search space by mapping inputs into a continuous latent space where familiar Bayesian optimization tools can be more readily applied. Despite this simplification, the latent space typically remains high-dimensional. Thus, even with a well-suited latent space, these approaches do not necessarily provide a complete solution, but may rather shift the structured optimization problem to a high-dimensional one. In this paper, we propose LOL-BO, which adapts the notion of trust regions explored in recent work on high-dimensional Bayesian optimization to the structured setting. By reformulating the encoder to function as both an encoder for the DAE globally and as a deep kernel for the surrogate model within a trust region, we better align the notion of local optimization in the latent space with local optimization in the input space. LOL-BO achieves as much as 20 times improvement over state-of-the-art latent space Bayesian optimization methods across six real-world benchmarks, demonstrating that improvement in optimization strategies is as important as developing better DAE models.

For agents

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

get_harvested_code_for_paper("2201.11872")
get_code_for_paper("2201.11872")
have("2201.11872")

Connect an agent — have() is free.