9 papers
LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?
Juliusz Ziomek, William Bankes, Lorenz Wolf +3
We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wi…
Canonical Regularisation of Wide Feature-Learning Neural Networks
George Whittle, Pranav Vaidhyanathan, Juliusz Ziomek +2
Wide neural networks in the feature-learning regime drive modern deep learning, and yet they remain far less studied than their kernel-regime counterparts. We consider a critical y…
Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation
George Whittle, Juliusz Ziomek, Jacob Rawling +1
While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractability of exact posterior computation, n…
Open-Ended Task Discovery via Bayesian Optimization
Masaki Adachi, Yuta Suzuki, Juliusz Ziomek
When applying Bayesian optimization (BO) to scientific workflow, a major yet often overlooked source of uncertainty is the task itself -- namely, what to optimize and how to evalua…
Just One Layer Norm Guarantees Stable Extrapolation
Juliusz Ziomek, George Whittle, Michael A. Osborne
In spite of their prevalence, the behaviour of Neural Networks when extrapolating far from the training distribution remains poorly understood, with existing results limited to spe…
Time-Varying Gaussian Process Bandits with Unknown Prior
Juliusz Ziomek, Masaki Adachi, Michael A. Osborne
Bayesian optimisation requires fitting a Gaussian process model, which in turn requires specifying prior on the unknown black-box function -- most of the theoretical literature ass…