Publications (28)
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…
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…
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…
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…
Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
Ayush Gupta, Ramneet Kaur, Anirban Roy +3
We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain…
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…