mlsanityData to 7 Oct 2026

An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization

arXiv 2210.16099 ↗First posted 27 Oct 2022q-bio.BM cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Molecule optimization is an important problem in chemical discovery and has been approached using many techniques, including generative modeling, reinforcement learning, genetic algorithms, and much more. Recent work has also applied zeroth-order (ZO) optimization, a subset of gradient-free optimization that solves problems similarly to gradient-based methods, for optimizing latent vector representations from an autoencoder. In this paper, we study the effectiveness of various ZO optimization methods for optimizing molecular objectives, which are characterized by variable smoothness, infrequent optima, and other challenges. We provide insights on the robustness of various ZO optimizers in this setting, show the advantages of ZO sign-based gradient descent (ZO-signGD), discuss how ZO optimization can be used practically in realistic discovery tasks, and demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite. Code is available at: https://github.com/IBM/QMO-bench.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

18 of 31 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  3. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  4. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  5. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  6. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  7. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  8. 2020A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learningcited by 160
  9. 2022Sample Efficiency Matters: A Benchmark for Practical Molecular Optimizationcited by 151
  10. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  11. 2017Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradientscited by 136
  12. 2018Learning Multimodal Graph-to-Graph Translation for Molecular Optimizationcited by 87
6 more
  1. 2020Optimizing Molecules using Efficient Queries from Property Evaluationscited by 50
  2. 2016A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Ordercited by 43
  3. 2019Model Agnostic Contrastive Explanations for Structured Datacited by 41
  4. 2021Oracle Complexity in Nonsmooth Nonconvex Optimizationcited by 38
  5. 2021DOCKSTRING: easy molecular docking yields better benchmarks for ligand designcited by 33
  6. 2021Zeroth-order Optimization for Composite Problems with Functional Constraintscited by 4

Built on by

Not cited yet.