Aitchison, Laurence

45 publications

ICLRW 2025 A Self-Improving Coding Agent Maxime Robeyns, Martin Szummer, Laurence Aitchison

TMLR 2025 Flexible Infinite-Width Graph Convolutional Neural Networks Ben Anson, Edward Milsom, Laurence Aitchison

ICML 2025 Function-Space Learning Rates Edward Milsom, Ben Anson, Laurence Aitchison

ICML 2025 How to Set AdamW’s Weight Decay as You Scale Model and Dataset Size Xi Wang, Laurence Aitchison

ICML 2025 Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations Lucy Farnik, Tim Lawson, Conor Houghton, Laurence Aitchison

ICML 2025 Position: Don’t Use the CLT in LLM Evals with Fewer than a Few Hundred Datapoints Sam Bowyer, Laurence Aitchison, Desi R. Ivanova

ICLR 2025 Residual Stream Analysis with Multi-Layer SAEs Tim Lawson, Lucy Farnik, Conor Houghton, Laurence Aitchison

NeurIPS 2025 Scale-Invariant Attention Ben Anson, Xi Wang, Laurence Aitchison

NeurIPSW 2024 Batch Size Invariant Adam Xi Wang, Laurence Aitchison

ICLR 2024 Bayesian Low-Rank Adaptation for Large Language Models Adam X. Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison

ICLRW 2024 Bayesian Reward Models for LLM Alignment Adam X. Yang, Maxime Robeyns, Thomas Coste, Jun Wang, Haitham Bou Ammar, Laurence Aitchison

ICMLW 2024 Bayesian Reward Models for LLM Alignment Adam X. Yang, Maxime Robeyns, Thomas Coste, Zhengyan Shi, Jun Wang, Haitham Bou Ammar, Laurence Aitchison

ICLR 2024 Convolutional Deep Kernel Machines Edward Milsom, Ben Anson, Laurence Aitchison

TMLR 2024 InfoNCE Is Variational Inference in a Recognition Parameterised Model Laurence Aitchison, Stoil Krasimirov Ganev

NeurIPS 2024 Instruction Tuning with Loss over Instructions Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani

ICMLW 2024 Instruction Tuning with Loss over Instructions Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani

NeurIPSW 2024 Inverse-Free Sparse Variational Gaussian Processes Stefano Cortinovis, Laurence Aitchison, James Hensman, Stefanos Eleftheriadis, Mark van der Wilk

ICMLW 2024 MONGOOSE: Path-Wise Smooth Bayesian Optimisation via Meta-Learning Adam X. Yang, Laurence Aitchison, Henry Moss

ICML 2024 Position: Bayesian Deep Learning Is Needed in the Age of Large-Scale AI Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, José Miguel Hernández-Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A Osborne, Tim G. J. Rudner, David Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang

NeurIPSW 2024 Residual Stream Analysis with Multi-Layer SAEs Tim Lawson, Lucy Farnik, Conor Houghton, Laurence Aitchison

NeurIPS 2024 Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines Edward Milsom, Ben Anson, Laurence Aitchison

UAI 2024 Using Autodiff to Estimate Posterior Moments, Marginals and Samples Sam Bowyer, Thomas Heap, Laurence Aitchison

ICML 2023 A Theory of Representation Learning Gives a Deep Generalisation of Kernel Methods Adam X. Yang, Maxime Robeyns, Edward Milsom, Ben Anson, Nandi Schoots, Laurence Aitchison

UAI 2023 An Improved Variational Approximate Posterior for the Deep Wishart Process Sebastian W. Ober, Ben Anson, Edward Milsom, Laurence Aitchison

NeurIPSW 2023 Bayesian Low-Rank Adaptation for Large Language Models Adam Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison

UAI 2023 Massively Parallel Reweighted Wake-Sleep Thomas Heap, Gavin Leech, Laurence Aitchison

ICLR 2023 Robustness to Corruption in Pre-Trained Bayesian Neural Networks Xi Wang, Laurence Aitchison

ICLR 2023 Semi-Supervised Learning with a Principled Likelihood from a Generative Model of Data Curation Stoil Krasimirov Ganev, Laurence Aitchison

NeurIPS 2023 Taylor TD-Learning Michele Garibbo, Maxime Robeyns, Laurence Aitchison

ICMLW 2023 Taylor TD-Learning Michele Garibbo, Maxime Robeyns, Laurence Aitchison

ICLR 2022 Bayesian Neural Network Priors Revisited Vincent Fortuin, Adrià Garriga-Alonso, Sebastian W. Ober, Florian Wenzel, Gunnar Ratsch, Richard E Turner, Mark van der Wilk, Laurence Aitchison

UAI 2022 Data Augmentation in Bayesian Neural Networks and the Cold Posterior Effect Seth Nabarro, Stoil Ganev, Adrià Garriga-Alonso, Vincent Fortuin, Mark Wilk, Laurence Aitchison

NeurIPSW 2022 Random Initialisations Performing Above Chance and How to Find Them Frederik Benzing, Simon Schug, Robert Meier, Johannes von Oswald, Yassir Akram, Nicolas Zucchet, Laurence Aitchison, Angelika Steger

ICLR 2021 A Statistical Theory of Cold Posteriors in Deep Neural Networks Laurence Aitchison

NeurIPS 2021 A Variational Approximate Posterior for the Deep Wishart Process Sebastian Ober, Laurence Aitchison

ICML 2021 Deep Kernel Processes Laurence Aitchison, Adam Yang, Sebastian W. Ober

ICML 2021 Global Inducing Point Variational Posteriors for Bayesian Neural Networks and Deep Gaussian Processes Sebastian W Ober, Laurence Aitchison

CoRL 2021 Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear Anupam K. Gupta, Laurence Aitchison, Nathan F. Lepora

NeurIPS 2020 Bayesian Filtering Unifies Adaptive and Non-Adaptive Neural Network Optimization Methods Laurence Aitchison

NeurIPSW 2020 Bayesian Neural Network Priors Revisited Vincent Fortuin, Adrià Garriga-Alonso, Florian Wenzel, Gunnar Ratsch, Richard E Turner, Mark van der Wilk, Laurence Aitchison

ICML 2020 Why Bigger Is Not Always Better: On Finite and Infinite Neural Networks Laurence Aitchison

ICLR 2019 Deep Convolutional Networks as Shallow Gaussian Processes Adrià Garriga-Alonso, Carl Edward Rasmussen, Laurence Aitchison

NeurIPS 2019 Tensor Monte Carlo: Particle Methods for the GPU Era Laurence Aitchison

NeurIPS 2017 Model-Based Bayesian Inference of Neural Activity and Connectivity from All-Optical Interrogation of a Neural Circuit Laurence Aitchison, Lloyd Russell, Adam M Packer, Jinyao Yan, Philippe Castonguay, Michael Hausser, Srinivas C. Turaga

NeurIPS 2014 Fast Sampling-Based Inference in Balanced Neuronal Networks Guillaume Hennequin, Laurence Aitchison, Mate Lengyel