# Time-Aware Latent Space Bayesian Optimization

arXiv: https://arxiv.org/abs/2603.00935 · HTML: https://mlsanity.com/paper/2603.00935/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Scalable Variational Gaussian Process Classification](https://mlsanity.com/paper/1411.2005/) (2014)
- [GP-VAE: Deep Probabilistic Time Series Imputation](https://mlsanity.com/paper/1907.04155/) (2019)
- [Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining](https://mlsanity.com/paper/2006.09191/) (2020)
- [Hilbert Space Methods for Reduced-Rank Gaussian Process Regression](https://mlsanity.com/paper/1401.5508/) (2014)
- [Local Latent Space Bayesian Optimization over Structured Inputs](https://mlsanity.com/paper/2201.11872/) (2022)
- [Gaussian Process Prior Variational Autoencoders](https://mlsanity.com/paper/1810.11738/) (2018)
- [High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning](https://mlsanity.com/paper/2106.03609/) (2021)
- [Time-Varying Gaussian Process Bandit Optimization](https://mlsanity.com/paper/1601.06650/) (2016)
- [Longitudinal Variational Autoencoder](https://mlsanity.com/paper/2006.09763/) (2020)
- [A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences](https://mlsanity.com/paper/2406.04739/) (2024)
- [Latent Bayesian Optimization via Autoregressive Normalizing Flows](https://mlsanity.com/paper/2504.14889/) (2025)
- [Advancing Bayesian Optimization via Learning Correlated Latent Space](https://mlsanity.com/paper/2310.20258/) (2023)
- [Tanimoto Random Features for Scalable Molecular Machine Learning](https://mlsanity.com/paper/2306.14809/) (2023)
- [Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces](https://mlsanity.com/paper/2507.03910/) (2025)
- [On Controller Tuning with Time-Varying Bayesian Optimization](https://mlsanity.com/paper/2207.11120/) (2022)
- [Inversion-based Latent Bayesian Optimization](https://mlsanity.com/paper/2411.05330/) (2024)
- [Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences](https://mlsanity.com/paper/2412.07763/) (2024)
- [This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization](https://mlsanity.com/paper/2405.14540/) (2024)
- [Crystal-LSBO: Automated Design of De Novo Crystals with Latent Space Bayesian Optimization](https://mlsanity.com/paper/2405.17881/) (2024)

## Built on by (most cited first, 1 of 1)

- [In-Context Learning for Latent Space Bayesian Optimization](https://mlsanity.com/paper/2606.09664/) (2026)

## Abstract (arXiv)

Latent-space Bayesian optimization (LSBO) extends Bayesian optimization to structured domains, such as molecular design, by searching in the continuous latent space of a generative model. However, most LSBO methods assume a fixed objective, whereas real design campaigns often face temporal drift (e.g., evolving preferences or shifting targets). Bringing time-varying BO into LSBO is nontrivial: drift can affect not only the surrogate, but also the latent search space geometry induced by the representation. We propose Time-Aware Latent-space Bayesian Optimization (TALBO), which incorporates time in both the surrogate and the learned generative representation via a GP-prior variational autoencoder, yielding a latent space aligned as objectives evolve. To evaluate timevarying LSBO systematically, we adapt widely used molecular design tasks to drifting multi-property objectives and introduce metrics tailored to changing targets. Across these benchmarks, TALBO consistently outperforms strong LSBO baselines and remains robust across drift speeds and design choices, while remaining competitive under actually time-invariant objectives.