12 citations · 39 across the 25 of their papers we have counts for
25 papers
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling
Yuche Gao, José Miguel Hernández-Lobato, Siyuan Guo
Predicting cellular responses to unseen chemical perturbations is challenging due to unknown targets and mechanisms, high-dimensional expression responses, and limited experimental…
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
RuiKang OuYang, Hanlin Yu, Xinyue Ai +7
Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, t…
Towards Diverse Scientific Hypothesis Search with Large Language Models
Haorui Wang, Parshin Shojaee, Kazem Meidani +7
Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses. Yet in many disc…
Free energy Estimation on Any State Space
Jiajun He, Zijing Ou, Francisco Vargas +4
Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimat…
On conditional diffusion models for PDE simulations
Aliaksandra Shysheya, Cristiana Diaconu, Federico Bergamin +4
Modelling partial differential equations (PDEs) is of crucial importance in science and engineering, and it includes tasks ranging from forecasting to inverse problems, such as dat…
Getting Free Bits Back from Rotational Symmetries in LLMs
Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato
Current methods for compressing neural network weights, such as decomposition, pruning, quantization, and channel simulation, often overlook the inherent symmetries within these ne…
Training Neural Samplers with Reverse Diffusive KL Divergence
Jiajun He, Wenlin Chen, Mingtian Zhang +2
Training generative models to sample from unnormalized density functions is an important and challenging task in machine learning. Traditional training methods often rely on the re…
Batched Bayesian optimization by maximizing the probability of including the optimum
Jenna Fromer, Runzhong Wang, Mrunali Manjrekar +3
Batched Bayesian optimization (BO) can accelerate molecular design by efficiently identifying top-performing compounds from a large chemical library. Existing acquisition strategie…
Best Practices for Multi-Fidelity Bayesian Optimization in Materials and Molecular Research
Víctor Sabanza-Gil, Riccardo Barbano, Daniel Pacheco Gutiérrez +4
Multi-fidelity Bayesian Optimization (MFBO) is a promising framework to speed up materials and molecular discovery as sources of information of different accuracies are at hand at…
Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models
Fengzhe Zhang, Jiajun He, Laurence I. Midgley +2
Diffusion models have shown promising potential for advancing Boltzmann Generators. However, two critical challenges persist: (1) inherent errors in samples due to model imperfecti…
BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching
RuiKang OuYang, Bo Qiang, José Miguel Hernández-Lobato
Developing an efficient sampler capable of generating independent and identically distributed (IID) samples from a Boltzmann distribution is a crucial challenge in scientific resea…
Diagnosing and fixing common problems in Bayesian optimization for molecule design
Austin Tripp, José Miguel Hernández-Lobato
Bayesian optimization (BO) is a principled approach to molecular design tasks. In this paper we explain three pitfalls of BO which can cause poor empirical performance: an incorrec…
Improving Antibody Design with Force-Guided Sampling in Diffusion Models
Paulina Kulytė, Francisco Vargas, Simon Valentin Mathis +3
Antibodies, crucial for immune defense, primarily rely on complementarity-determining regions (CDRs) to bind and neutralize antigens, such as viruses. The design of these CDRs dete…
Warm Start Marginal Likelihood Optimisation for Iterative Gaussian Processes
Jihao Andreas Lin, Shreyas Padhy, Bruno Mlodozeniec +1
Gaussian processes are a versatile probabilistic machine learning model whose effectiveness often depends on good hyperparameters, which are typically learned by maximising the mar…
Generative Active Learning for the Search of Small-molecule Protein Binders
Maksym Korablyov, Cheng-Hao Liu, Moksh Jain +31
Despite substantial progress in machine learning for scientific discovery in recent years, truly de novo design of small molecules which exhibit a property of interest remains a si…
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Jihao Andreas Lin, Shreyas Padhy, Bruno Mlodozeniec +2
Scaling hyperparameter optimisation to very large datasets remains an open problem in the Gaussian process community. This paper focuses on iterative methods, which use linear syst…
Accelerating Relative Entropy Coding with Space Partitioning
Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato
Relative entropy coding (REC) algorithms encode a random sample following a target distribution , using a coding distribution shared between the sender and receiver. Sadly,…
A Generative Model of Symmetry Transformations
James Urquhart Allingham, Bruno Kacper Mlodozeniec, Shreyas Padhy +5
Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require…
Diffusive Gibbs Sampling
Wenlin Chen, Mingtian Zhang, Brooks Paige +2
The inadequate mixing of conventional Markov Chain Monte Carlo (MCMC) methods for multi-modal distributions presents a significant challenge in practical applications such as Bayes…
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla +22
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language dat…
Genetic algorithms are strong baselines for molecule generation
Austin Tripp, José Miguel Hernández-Lobato
Generating molecules, both in a directed and undirected fashion, is a huge part of the drug discovery pipeline. Genetic algorithms (GAs) generate molecules by randomly modifying kn…
Stochastic Gradient Descent for Gaussian Processes Done Right
Jihao Andreas Lin, Shreyas Padhy, Javier Antorán +5
As is well known, both sampling from the posterior and computing the mean of the posterior in Gaussian process regression reduces to solving a large linear system of equations. We…
Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens
Ross M. Clarke, José Miguel Hernández-Lobato
Research into optimisation for deep learning is characterised by a tension between the computational efficiency of first-order, gradient-based methods (such as SGD and Adam) and th…
Series of Hessian-Vector Products for Tractable Saddle-Free Newton Optimisation of Neural Networks
Elre T. Oldewage, Ross M. Clarke, José Miguel Hernández-Lobato
Despite their popularity in the field of continuous optimisation, second-order quasi-Newton methods are challenging to apply in machine learning, as the Hessian matrix is intractab…