Laurence Aitchison
30 papers · 2014–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (48) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
👑
Triple Crown
🏆
Keyword Champion
(3)
👥
Mega-Team · Squad
🔬
Deep Specialist
(17)
🌈
Renaissance Researcher
(6)
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(127)
Venues
Top co-authors
Research topics
Machine Learning
(28)
Optimization & Theory
(24)
Deep Learning
(18)
Artificial Intelligence
(17)
Bayesian & Probabilistic · Artificial Intelligence
(11)
Models
(10)
Core Methods
(8)
Architectures
(7)
Bayesian & Probabilistic · Machine Learning
(6)
Core AI
(6)
Learning Types
(5)
Learning Paradigms
(4)
Natural Language Processing
(3)
Resources & Methods
(3)
Techniques
(3)
Keywords
variational inference
(8)
bayesian inference
(7)
bayesian neural network
(6)
gaussian process
(5)
representation learning
(4)
kernel methods
(4)
large language model
(3)
deep kernel machine
(3)
convolutional neural network
(3)
deep gaussian process
(3)
generative model
(3)
image classification
(3)
importance sampling
(3)
stochastic gradient descent
(2)
cold posterior
(2)
deep wishart process
(2)
deep kernel process
(2)
latent variable model
(2)
variational autoencoder
(2)
entropy minimization
(1)
Papers
Function-Space Learning Rates
ICML 2025
How to set AdamW’s weight decay as you scale model and dataset size
ICML 2025
Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
ICML 2025
Position: Don’t Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
ICML 2025
Residual Stream Analysis with Multi-Layer SAEs
ICLR 2025
Bayesian Low-rank Adaptation for Large Language Models
ICLR 2024
Convolutional Deep Kernel Machines
ICLR 2024
Instruction Tuning With Loss Over Instructions
NeurIPS 2024
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
ICML 2024
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
NeurIPS 2024
Using Autodiff to Estimate Posterior Moments, Marginals and Samples
UAI 2024
An improved variational approximate posterior for the deep Wishart process
UAI 2023
A theory of representation learning gives a deep generalisation of kernel methods
ICML 2023
Massively parallel reweighted wake-sleep
UAI 2023
Robustness to corruption in pre-trained Bayesian neural networks
ICLR 2023
Semi-supervised learning with a principled likelihood from a generative model of data curation
ICLR 2023
Taylor TD-learning
NeurIPS 2023
Bayesian Neural Network Priors Revisited
ICLR 2022
Data augmentation in Bayesian neural networks and the cold posterior effect
UAI 2022
A statistical theory of cold posteriors in deep neural networks
ICLR 2021
A variational approximate posterior for the deep Wishart process
NeurIPS 2021
Deep kernel processes
ICML 2021
Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
ICML 2021
Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear
CoRL 2021
Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods
NeurIPS 2020
Why bigger is not always better: on finite and infinite neural networks
ICML 2020
Deep Convolutional Networks as shallow Gaussian Processes
ICLR 2019
Tensor Monte Carlo: Particle Methods for the GPU era
NeurIPS 2019
Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit
NeurIPS 2017
Fast Sampling-Based Inference in Balanced Neuronal Networks
NeurIPS 2014