67 citations · 233 across the 19 of their papers we have counts for
20 papers
Direct Amortized Likelihood Ratio Estimation
Adam D. Cobb, Brian Matejek, Daniel Elenius +2
We introduce a new amortized likelihood ratio estimator for likelihood-free simulation-based inference (SBI). Our estimator is simple to train and estimates the likelihood ratio us…
AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
Adam D. Cobb, Anirban Roy, Daniel Elenius +9
We present AircraftVerse, a publicly available aerial vehicle design dataset. Aircraft design encompasses different physics domains and, hence, multiple modalities of representatio…
On Sequential Bayesian Inference for Continual Learning
Samuel Kessler, Adam Cobb, Tim G. J. Rudner +2
Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revis…
Design of Unmanned Air Vehicles Using Transformer Surrogate Models
Adam D. Cobb, Anirban Roy, Daniel Elenius +1
Computer-aided design (CAD) is a promising new area for the application of artificial intelligence (AI) and machine learning (ML). The current practice of design of cyber-physical…
Principal Manifold Flows
Edmond Cunningham, Adam Cobb, Susmit Jha
Normalizing flows map an independent set of latent variables to their samples using a bijective transformation. Despite the exact correspondence between samples and latent variable…
Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning
Meet P. Vadera, Adam D. Cobb, Brian Jalaian +1
Bayesian methods hold significant promise for improving the uncertainty quantification ability and robustness of deep neural network models. Recent research has seen the investigat…
HumBugDB: A Large-scale Acoustic Mosquito Dataset
Ivan Kiskin, Marianne Sinka, Adam D. Cobb +13
This paper presents the first large-scale multi-species dataset of acoustic recordings of mosquitoes tracked continuously in free flight. We present 20 hours of audio recordings th…
Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlo
Vyacheslav Kungurtsev, Adam Cobb, Tara Javidi +1
Federated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices. Bayesian appro…
Better call Surrogates: A hybrid Evolutionary Algorithm for Hyperparameter optimization
Subhodip Biswas, Adam D Cobb, Andreea Sistrunk +2
In this paper, we propose a surrogate-assisted evolutionary algorithm (EA) for hyperparameter optimization of machine learning (ML) models. The proposed STEADE model initially esti…
Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
Adam D. Cobb, Brian Jalaian
Hamiltonian Monte Carlo (HMC) is a Markov chain Monte Carlo (MCMC) approach that exhibits favourable exploration properties in high-dimensional models such as neural networks. Unfo…
URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks
Meet P. Vadera, Adam D. Cobb, Brian Jalaian +1
While deep learning methods continue to improve in predictive accuracy on a wide range of application domains, significant issues remain with other aspects of their performance inc…
Accurate Machine Learning Atmospheric Retrieval via a Neural Network Surrogate Model for Radiative Transfer
Michael D. Himes, Joseph Harrington, Adam D. Cobb +8
Atmospheric retrieval determines the properties of an atmosphere based on its measured spectrum. The low signal-to-noise ratio of exoplanet observations require a Bayesian approach…
HumBug Zooniverse: a crowd-sourced acoustic mosquito dataset
Ivan Kiskin, Adam D. Cobb, Lawrence Wang +1
Mosquitoes are the only known vector of malaria, which leads to hundreds of thousands of deaths each year. Understanding the number and location of potential mosquito vectors is of…
Introducing an Explicit Symplectic Integration Scheme for Riemannian Manifold Hamiltonian Monte Carlo
Adam D. Cobb, Atılım Güneş Baydin, Andrew Markham +1
We introduce a recent symplectic integration scheme derived for solving physically motivated systems with non-separable Hamiltonians. We show its relevance to Riemannian manifold H…
An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval
Adam D. Cobb, Michael D. Himes, Frank Soboczenski +7
Machine learning is now used in many areas of astrophysics, from detecting exoplanets in Kepler transit signals to removing telescope systematics. Recent work demonstrated the pote…
Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer's disease severity
Wolfgang Fruehwirt, Adam D. Cobb, Martin Mairhofer +11
As societies around the world are ageing, the number of Alzheimer's disease (AD) patients is rapidly increasing. To date, no low-cost, non-invasive biomarkers have been established…
Bayesian Deep Learning for Exoplanet Atmospheric Retrieval
Frank Soboczenski, Michael D. Himes, Molly D. O'Beirne +8
Over the past decade, the study of extrasolar planets has evolved rapidly from plain detection and identification to comprehensive categorization and characterization of exoplanet…
Loss-Calibrated Approximate Inference in Bayesian Neural Networks
Adam D. Cobb, Stephen J. Roberts, Yarin Gal
Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this…
Identifying Sources and Sinks in the Presence of Multiple Agents with Gaussian Process Vector Calculus
Adam D. Cobb, Richard Everett, Andrew Markham +1
In systems of multiple agents, identifying the cause of observed agent dynamics is challenging. Often, these agents operate in diverse, non-stationary environments, where models re…
Learning from lions: inferring the utility of agents from their trajectories
Adam D. Cobb, Andrew Markham, Stephen J. Roberts
We build a model using Gaussian processes to infer a spatio-temporal vector field from observed agent trajectories. Significant landmarks or influence points in agent surroundings…