Laurence Aitchison

100 papers A* 21A 4Misc 1Journal 67Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference. CoRR David Fox, Sam Bowyer, Song Liu, Laurence Aitchison, Raul Santos-Rodriguez, Mengyue Yang
2026	J	`jnl`	Rodent-Bench. CoRR Thomas Heap, Laurence Aitchison, Emma Cahill, Adriana Casado Rodriguez
2025	J	`jnl`	A Self-Improving Coding Agent. CoRR Maxime Robeyns, Martin Szummer, Laurence Aitchison
2025	J	`jnl`	Controlling changes to attention logits. CoRR Ben Anson, Laurence Aitchison
2025	J	`jnl`	Flexible Infinite-Width Graph Convolutional Neural Networks. Trans. Mach. Learn. Res. Ben Anson, Edward Milsom, Laurence Aitchison
2025	A*	`conf`	Function-Space Learning Rates. ICML Edward Milsom, Ben Anson, Laurence Aitchison
2025	J	`jnl`	Function-Space Learning Rates. CoRR Edward Milsom, Ben Anson, Laurence Aitchison
2025	A*	`conf`	How to set AdamW's weight decay as you scale model and dataset size. ICML Xi Wang, Laurence Aitchison
2025	J	`jnl`	Improving LLM-Generated Code Quality with GRPO. CoRR Maxime Robeyns, Laurence Aitchison
2025	A*	`conf`	Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations. ICML Lucy Farnik, Tim Lawson, Conor J. Houghton, Laurence Aitchison
2025	J	`jnl`	Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations. CoRR Lucy Farnik, Tim Lawson, Conor J. Houghton, Laurence Aitchison
2025	J	`jnl`	Learning to Skip the Middle Layers of Transformers. CoRR Tim Lawson, Laurence Aitchison
2025	—	`conf`	Massively Parallel Expectation Maximization For Approximate Posteriors. AABI Thomas Heap, Sam Bowyer, Laurence Aitchison
2025	J	`jnl`	Massively Parallel Expectation Maximization For Approximate Posteriors. CoRR Thomas Heap, Sam Bowyer, Laurence Aitchison
2025	—	`conf`	Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints. ICML (Position Papers) Sam Bowyer, Laurence Aitchison, Desi R. Ivanova
2025	J	`jnl`	Position: Don't use the CLT in LLM evals with fewer than a few hundred datapoints. CoRR Sam Bowyer, Laurence Aitchison, Desi R. Ivanova
2025	A*	`conf`	Residual Stream Analysis with Multi-Layer SAEs. ICLR Tim Lawson, Lucy Farnik, Conor J. Houghton, Laurence Aitchison
2025	J	`jnl`	Scale-invariant Attention. CoRR Ben Anson, Xi Wang, Laurence Aitchison
2025	—	`conf`	Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces. 3DV Mauro Comi, Alessio Tonioni, Jonathan Tremblay, Max Yang, Valts Blukis, Yijiong Lin, Nathan F. Lepora, Laurence Aitchison
2025	J	`jnl`	Sparse Autoencoders Can Interpret Randomly Initialized Transformers. CoRR Thomas Heap, Tim Lawson, Lucy Farnik, Laurence Aitchison
2024	J	`jnl`	Batch size invariant Adam. CoRR Xi Wang, Laurence Aitchison
2024	A*	`conf`	Bayesian Low-rank Adaptation for Large Language Models. ICLR Adam X. Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison
2024	J	`jnl`	Bayesian Reward Models for LLM Alignment. CoRR Adam X. Yang, Maxime Robeyns, Thomas Coste, Jun Wang, Haitham Bou-Ammar, Laurence Aitchison
2024	A*	`conf`	Convolutional Deep Kernel Machines. ICLR Edward Milsom, Ben Anson, Laurence Aitchison
2024	J	`jnl`	Flexible infinite-width graph convolutional networks and the importance of representation learning. CoRR Ben Anson, Edward Milsom, Laurence Aitchison
2024	J	`jnl`	How to set AdamW's weight decay as you scale model and dataset size. CoRR Xi Wang, Laurence Aitchison
2024	J	`jnl`	Human-inspired Perspectives: A Survey on AI Long-term Memory. CoRR Zihong He, Weizhe Lin, Hao Zheng, Fan Zhang, Matt W. Jones, Laurence Aitchison, Xuhai Xu, Miao Liu, Per Ola Kristensson, Junxiao Shen
2024	J	`jnl`	InfoNCE is variational inference in a recognition parameterised model. Trans. Mach. Learn. Res. Laurence Aitchison, Stoil Ganev
2024	A*	`conf`	Instruction Tuning With Loss Over Instructions. NeurIPS Zhengxiang Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani
2024	J	`jnl`	Instruction Tuning With Loss Over Instructions. CoRR Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani
2024	J	`jnl`	Machine learning emulation of precipitation from km-scale regional climate simulations using a diffusion model. CoRR Henry Addison, Elizabeth Kendon, Suman V. Ravuri, Laurence Aitchison, Peter A. G. Watson
2024	J	`jnl`	Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI. CoRR Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David B. 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
2024	A*	`conf`	Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI. ICML Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David B. 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
2024	J	`jnl`	Questionable practices in machine learning. CoRR Gavin Leech, Juan J. Vazquez, Misha Yagudin, Niclas Kupper, Laurence Aitchison
2024	J	`jnl`	Relating Human Error-Based Learning to Modern Deep RL Algorithms. Neural Comput. Michele Garibbo, Casimir J. H. Ludwig, Nathan F. Lepora, Laurence Aitchison
2024	J	`jnl`	Residual Stream Analysis with Multi-Layer SAEs. CoRR Tim Lawson, Lucy Farnik, Conor J. Houghton, Laurence Aitchison
2024	J	`jnl`	Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces. CoRR Mauro Comi, Alessio Tonioni, Max Yang, Jonathan Tremblay, Valts Blukis, Yijiong Lin, Nathan F. Lepora, Laurence Aitchison
2024	A*	`conf`	Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines. NeurIPS Edward Milsom, Ben Anson, Laurence Aitchison
2024	J	`jnl`	Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines. CoRR Edward Milsom, Ben Anson, Laurence Aitchison
2024	J	`jnl`	TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction Using Vision-Based Tactile Sensing. IEEE Robotics Autom. Lett. Mauro Comi, Yijiong Lin, Alex Church, Alessio Tonioni, Laurence Aitchison, Nathan F. Lepora
2024	A	`conf`	Using Autodiff to Estimate Posterior Moments, Marginals and Samples. UAI Sam Bowyer, Thomas Heap, Laurence Aitchison
2024	J	`jnl`	Using Neural Networks for Data Cleaning in Weather Datasets. CoRR Jack R. P. Hanslope, Laurence Aitchison
2024	J	`jnl`	Why you don't overfit, and don't need Bayes if you only train for one epoch. CoRR Laurence Aitchison
2023	A*	`conf`	A theory of representation learning gives a deep generalisation of kernel methods. ICML Adam X. Yang, Maxime Robeyns, Edward Milsom, Ben Anson, Nandi Schoots, Laurence Aitchison
2023	J	`jnl`	An Improved Variational Approximate Posterior for the Deep Wishart Process. CoRR Sebastian W. Ober, Ben Anson, Edward Milsom, Laurence Aitchison
2023	A	`conf`	An improved variational approximate posterior for the deep Wishart process. UAI Sebastian W. Ober, Ben Anson, Edward Milsom, Laurence Aitchison
2023	J	`jnl`	Bayesian low-rank adaptation for large language models. CoRR Adam X. Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison
2023	J	`jnl`	Convolutional Deep Kernel Machines. CoRR Edward Milsom, Ben Anson, Laurence Aitchison
2023	J	`jnl`	Decision trees compensate for model misspecification. CoRR Hugh Panton, Gavin Leech, Laurence Aitchison
2023	J	`jnl`	Imitating careful experts to avoid catastrophic events. CoRR Jack R. P. Hanslope, Laurence Aitchison
2023	J	`jnl`	LoRA ensembles for large language model fine-tuning. CoRR Xi Wang, Laurence Aitchison, Maja Rudolph
2023	J	`jnl`	MONGOOSE: Path-wise Smooth Bayesian Optimisation via Meta-learning. CoRR Adam X. Yang, Laurence Aitchison, Henry B. Moss
2023	J	`jnl`	Massively Parallel Reweighted Wake-Sleep. CoRR Thomas Heap, Gavin Leech, Laurence Aitchison
2023	A	`conf`	Massively parallel reweighted wake-sleep. UAI Thomas Heap, Gavin Leech, Laurence Aitchison
2023	A*	`conf`	Robustness to corruption in pre-trained Bayesian neural networks. ICLR Xi Wang, Laurence Aitchison
2023	A*	`conf`	Semi-supervised learning with a principled likelihood from a generative model of data curation. ICLR Stoil Ganev, Laurence Aitchison
2023	A*	`conf`	Taylor TD-learning. NeurIPS Michele Garibbo, Maxime Robeyns, Laurence Aitchison
2023	J	`jnl`	Taylor TD-learning. CoRR Michele Garibbo, Maxime Robeyns, Laurence Aitchison
2023	J	`jnl`	TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing. CoRR Mauro Comi, Yijiong Lin, Alex Church, Alessio Tonioni, Laurence Aitchison, Nathan F. Lepora
2022	—	`conf`	Active Inference for Artificial Touch: A Biologically-Plausible Tactile Control Method. Living Machines Pernilla Craig, Laurence Aitchison, Nathan F. Lepora
2022	A*	`conf`	Bayesian Neural Network Priors Revisited. ICLR Vincent Fortuin, Adrià Garriga-Alonso, Sebastian W. Ober, Florian Wenzel, Gunnar Rätsch, Richard E. Turner, Mark van der Wilk, Laurence Aitchison
2022	A	`conf`	Data augmentation in Bayesian neural networks and the cold posterior effect. UAI Seth Nabarro, Stoil Ganev, Adrià Garriga-Alonso, Vincent Fortuin, Mark van der Wilk, Laurence Aitchison
2022	J	`jnl`	Machine learning emulation of a local-scale UK climate model. CoRR Henry Addison, Elizabeth Kendon, Suman V. Ravuri, Laurence Aitchison, Peter A. G. Watson
2022	J	`jnl`	Out of distribution robustness with pre-trained Bayesian neural networks. CoRR Xi Wang, Laurence Aitchison
2022	J	`jnl`	Random initialisations performing above chance and how to find them. CoRR Frederik Benzing, Simon Schug, Robert Meier, Johannes von Oswald, Yassir Akram, Nicolas Zucchet, Laurence Aitchison, Angelika Steger
2022	J	`jnl`	What deep reinforcement learning tells us about human motor learning and vice-versa. CoRR Michele Garibbo, Casimir J. H. Ludwig, Nathan F. Lepora, Laurence Aitchison
2021	J	`jnl`	A fast point solver for deep nonlinear function approximators. CoRR Laurence Aitchison
2021	A*	`conf`	A statistical theory of cold posteriors in deep neural networks. ICLR Laurence Aitchison
2021	J	`jnl`	A statistical theory of out-of-distribution detection. CoRR Xi Wang, Laurence Aitchison
2021	A*	`conf`	A variational approximate posterior for the deep Wishart process. NeurIPS Sebastian W. Ober, Laurence Aitchison
2021	J	`jnl`	A variational approximate posterior for the deep Wishart process. CoRR Sebastian W. Ober, Laurence Aitchison
2021	J	`jnl`	BNNpriors: A library for Bayesian neural network inference with different prior distributions. CoRR Vincent Fortuin, Adrià Garriga-Alonso, Mark van der Wilk, Laurence Aitchison
2021	J	`jnl`	Bayesian Neural Network Priors Revisited. CoRR Vincent Fortuin, Adrià Garriga-Alonso, Florian Wenzel, Gunnar Rätsch, Richard E. Turner, Mark van der Wilk, Laurence Aitchison
2021	J	`jnl`	Data augmentation in Bayesian neural networks and the cold posterior effect. CoRR Seth Nabarro, Stoil Ganev, Adrià Garriga-Alonso, Vincent Fortuin, Mark van der Wilk, Laurence Aitchison
2021	A*	`conf`	Deep Kernel Processes. ICML Laurence Aitchison, Adam X. Yang, Sebastian W. Ober
2021	A*	`conf`	Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes. ICML Sebastian W. Ober, Laurence Aitchison
2021	J	`jnl`	Gradient Regularization as Approximate Variational Inference. Entropy Ali Unlu, Laurence Aitchison
2021	J	`jnl`	InfoNCE is a variational autoencoder. CoRR Laurence Aitchison
2021	Misc	`conf`	Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear. CoRL Anupam K. Gupta, Laurence Aitchison, Nathan F. Lepora
2021	J	`jnl`	Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear. CoRR Anupam K. Gupta, Laurence Aitchison, Nathan F. Lepora
2020	J	`jnl`	A statistical theory of cold posteriors in deep neural networks. CoRR Laurence Aitchison
2020	J	`jnl`	A statistical theory of semi-supervised learning. CoRR Laurence Aitchison
2020	A*	`conf`	Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods. NeurIPS Laurence Aitchison
2020	J	`jnl`	Deep kernel processes. CoRR Laurence Aitchison, Adam X. Yang, Sebastian W. Ober
2020	J	`jnl`	Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes. CoRR Sebastian W. Ober, Laurence Aitchison
2020	J	`jnl`	Gradient Regularisation as Approximate Variational Inference. CoRR Ali Unlu, Laurence Aitchison
2020	J	`jnl`	Legally grounded fairness objectives. CoRR Dylan Holden-Sim, Gavin Leech, Laurence Aitchison
2020	A*	`conf`	Why bigger is not always better: on finite and infinite neural networks. ICML Laurence Aitchison
2019	—	`conf`	Deep Convolutional Networks as shallow Gaussian Processes. ICLR (Poster) Adrià Garriga-Alonso, Carl Edward Rasmussen, Laurence Aitchison
2019	A*	`conf`	Tensor Monte Carlo: Particle Methods for the GPU era. NeurIPS Laurence Aitchison
2019	J	`jnl`	Why bigger is not always better: on finite and infinite neural networks. CoRR Laurence Aitchison
2018	J	`jnl`	A unified theory of adaptive stochastic gradient descent as Bayesian filtering. CoRR Laurence Aitchison
2018	J	`jnl`	Deep Convolutional Networks as shallow Gaussian Processes. CoRR Adrià Garriga-Alonso, Laurence Aitchison, Carl Edward Rasmussen
2018	J	`jnl`	Discrete flow posteriors for variational inference in discrete dynamical systems. CoRR Laurence Aitchison, Vincent Adam, Srinivas C. Turaga
2018	J	`jnl`	Tensor Monte Carlo: particle methods for the GPU era. CoRR Laurence Aitchison
2017	—	`conf`	Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit. NIPS Laurence Aitchison, Lloyd Russell, Adam M. Packer, Jinyao Yan, Philippe Castonguay, Michael Häusser, Srinivas C. Turaga
2016	J	`jnl`	The Hamiltonian Brain: Efficient Probabilistic Inference with Excitatory-Inhibitory Neural Circuit Dynamics. PLoS Comput. Biol. Laurence Aitchison, Máté Lengyel
2016	J	`jnl`	Zipf's Law Arises Naturally When There Are Underlying, Unobserved Variables. PLoS Comput. Biol. Laurence Aitchison, Nicola Corradi, Peter E. Latham
2015	J	`jnl`	Doubly Bayesian Analysis of Confidence in Perceptual Decision-Making. PLoS Comput. Biol. Laurence Aitchison, Dan Bang, Bahador Bahrami, Peter E. Latham
2014	—	`conf`	Fast Sampling-Based Inference in Balanced Neuronal Networks. NIPS Guillaume Hennequin, Laurence Aitchison, Máté Lengyel