2 citations · 6 across the 14 of their papers we have counts for
15 papers
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…
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…
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…
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…
Mean-Field Bayesian Optimisation
Petar Steinberg, Juliusz Ziomek, Matej Jusup +1
We address the problem of optimising the average payoff for a large number of cooperating agents, where the payoff function is unknown and treated as a black box. While standard Ba…
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…
Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal
Juliusz Ziomek, Masaki Adachi, Michael A. Osborne
Bayesian Optimization (BO) is widely used for optimising black-box functions but requires us to specify the length scale hyperparameter, which defines the smoothness of the functio…
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…
Why Can Large Language Models Generate Correct Chain-of-Thoughts?
Rasul Tutunov, Antoine Grosnit, Juliusz Ziomek +2
This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investig…
Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?
Juliusz Ziomek, Haitham Bou-Ammar
Learning decompositions of expensive-to-evaluate black-box functions promises to scale Bayesian optimisation (BO) to high-dimensional problems. However, the success of these techni…
Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
Taher Jafferjee, Juliusz Ziomek, Tianpei Yang +6
Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it…
Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints
David Mguni, Aivar Sootla, Juliusz Ziomek +4
Many real-world settings involve costs for performing actions; transaction costs in financial systems and fuel costs being common examples. In these settings, performing actions at…
Modelling nonlinear dependencies in the latent space of inverse scattering
Juliusz Ziomek, Katayoun Farrahi
The problem of inverse scattering proposed by Angles and Mallat in 2018, concerns training a deep neural network to invert the scattering transform applied to an image. After such…
Settling the Communication Complexity for Distributed Offline Reinforcement Learning
Juliusz Krysztof Ziomek, Jun Wang, Yaodong Yang
We study a novel setting in offline reinforcement learning (RL) where a number of distributed machines jointly cooperate to solve the problem but only one single round of communica…
Research on rolling friction's dependence on ball bearings' radius
Grzegorz M. Koczan, Juliusz Ziomek
There are two alternative historical laws of rolling resistance formulated by French scientist Coulomb and Dupuit. It has been decided to verify experimentally again, which of thes…