Search Results for author:
Found 44 papers, 20 papers with code
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
We theoretically analyse the convergence of NS-DPO in the offline setting, providing upper bounds on the estimation error caused by non-stationary preferences.
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
To address this, we propose a novel method, WALLE, which leverages both unstructured modeling from protein language models and structural modeling from graph neural networks.
Analyzing the Generalization and Reliability of Steering Vectors
In this work, we rigorously investigate these properties, and show that steering vectors have substantial limitations both in- and out-of-distribution.
Generative Active Learning for the Search of Small-molecule Protein Binders
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 significant challenge.
Can a Confident Prior Replace a Cold Posterior?
First, we introduce a "DirClip" prior that is practical to sample and nearly matches the performance of a cold posterior.
Diffusive Gibbs Sampling
The inadequate mixing of conventional Markov Chain Monte Carlo (MCMC) methods for multi-modal distributions presents a significant challenge in practical applications such as Bayesian inference and molecular dynamics.
Gaussian Processes on Cellular Complexes
In this paper, we go beyond this dyadic setting and consider polyadic relations that include interactions between vertices, edges and one of their generalisations, known as cells.
Moment Matching Denoising Gibbs Sampling
Energy-Based Models (EBMs) offer a versatile framework for modeling complex data distributions.
Towards Healing the Blindness of Score Matching
Score-based divergences have been widely used in machine learning and statistics applications.
Improving VAE-based Representation Learning
Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images.
Simulation Intelligence: Towards a New Generation of Scientific Methods
We present the "Nine Motifs of Simulation Intelligence", a roadmap for the development and integration of the essential algorithms necessary for a merger of scientific computing, scientific simulation, and artificial intelligence.
Probabilistic Deep Learning with Generalised Variational Inference
We study probabilistic Deep Learning methods through the lens of Approximate Bayesian Inference.
Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processes
Variable selection in Gaussian processes (GPs) is typically undertaken by thresholding the inverse lengthscales of automatic relevance determination kernels, but in high-dimensional datasets this approach can be unreliable.
I Don't Need u: Identifiable Non-Linear ICA Without Side Information
Surprisingly, we discover side information is not necessary for algorithmic stability: using standard quantitative measures of identifiability, we find deep generative models with latent clusterings are empirically identifiable to the same degree as models which rely on auxiliary labels.
Barking up the right tree: an approach to search over molecule synthesis DAGs
When designing new molecules with particular properties, it is not only important what to make but crucially how to make it.
Bayesian Graph Neural Networks for Molecular Property Prediction
Graph neural networks for molecular property prediction are frequently underspecified by data and fail to generalise to new scaffolds at test time.
Making Graph Neural Networks Worth It for Low-Data Molecular Machine Learning
When we find that they are not, we explore pretraining and the meta-learning method MAML (and variants FO-MAML and ANIL) for improving graph neural network performance by transfer learning from related tasks.
Goal-directed Generation of Discrete Structures with Conditional Generative Models
Unfortunately, maximum likelihood training of such models often fails with the samples from the generative model inadequately respecting the input properties.
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Multimodal learning for generative models often refers to the learning of abstract concepts from the commonality of information in multiple modalities, such as vision and language.
Learning Bijective Feature Maps for Linear ICA
Separating high-dimensional data like images into independent latent factors, i. e independent component analysis (ICA), remains an open research problem.
Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models
In this work, we characterise successful learning of such models as the fulfillment of four criteria: i) implicit latent decomposition into shared and private subspaces, ii) coherent joint generation over all modalities, iii) coherent cross-generation across individual modalities, and iv) improved model learning for individual modalities through multi-modal integration.
Data Generation for Neural Programming by Example
A particular challenge lies in generating meaningful sets of inputs and outputs, which well-characterize a given program and accurately demonstrate its behavior.
Conditional generation of molecules from disentangled representations
Though machine learning approaches have shown great success in estimating properties of small molecules, the inverse problem of generating molecules with desired properties remains challenging.
A Model to Search for Synthesizable Molecules
Deep generative models are able to suggest new organic molecules by generating strings, trees, and graphs representing their structure.
Generating Molecules via Chemical Reactions
We therefore propose a new molecule generation model, mirroring a more realistic real-world process, where reactants are selected and combined to form more complex molecules.
An Introduction to Probabilistic Programming
We start with a discussion of model-based reasoning and explain why conditioning is a foundational computation central to the fields of probabilistic machine learning and artificial intelligence.
Take a Look Around: Using Street View and Satellite Images to Estimate House Prices
Not only do few quantitative methods exist that can measure the urban environment, but that the collection of such data is both costly and subjective.
A Generative Model For Electron Paths
Chemical reactions can be described as the stepwise redistribution of electrons in molecules.
Structured Disentangled Representations
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner.
Learning a Generative Model for Validity in Complex Discrete Structures
This validator provides insight as to how individual sequence elements influence the validity of the overall sequence, and can be used to constrain sequence based models to generate valid sequences -- and thus faithfully model discrete objects.
Learning Disentangled Representations with Semi-Supervised Deep Generative Models
We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder.
Grammar Variational Autoencoder
Crucially, state-of-the-art methods often produce outputs that are not valid.
Inducing Interpretable Representations with Variational Autoencoders
We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational inference.
Probabilistic structure discovery in time series data
Existing methods for structure discovery in time series data construct interpretable, compositional kernels for Gaussian process regression models.
Inference Networks for Sequential Monte Carlo in Graphical Models
We introduce a new approach for amortizing inference in directed graphical models by learning heuristic approximations to stochastic inverses, designed specifically for use as proposal distributions in sequential Monte Carlo methods.
Interacting Particle Markov Chain Monte Carlo
We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a PMCMC method based on an interacting pool of standard and conditional sequential Monte Carlo samplers.
Kernel Sequential Monte Carlo
As KSMC does not require access to target gradients, it is particularly applicable on targets whose gradients are unknown or prohibitively expensive.
Black-Box Policy Search with Probabilistic Programs
In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems.
Path Finding under Uncertainty through Probabilistic Inference
We introduce a new approach to solving path-finding problems under uncertainty by representing them as probabilistic models and applying domain-independent inference algorithms to the models.
Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs
We introduce an adaptive output-sensitive Metropolis-Hastings algorithm for probabilistic models expressed as programs, Adaptive Lightweight Metropolis-Hastings (AdLMH).
Asynchronous Anytime Sequential Monte Carlo
We introduce a new sequential Monte Carlo algorithm we call the particle cascade.
A Compilation Target for Probabilistic Programming Languages
Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory.
Tempering by Subsampling
In this paper we demonstrate that tempering Markov chain Monte Carlo samplers for Bayesian models by recursively subsampling observations without replacement can improve the performance of baseline samplers in terms of effective sample size per computation.
Bayesian Inference and Online Experimental Design for Mapping Neural Microcircuits
We develop an inference and optimal design procedure for recovering synaptic weights in neural microcircuits.
