AIConfPaper
← Search

Jonathan Wilder Lavington

6 accepted papers

2024

Nearest Neighbour Score Estimators for Diffusion Generative Models

Matthew Niedoba, Dylan Green, Saeid Naderiparizi, Vasileios Lioutas, Jonathan Wilder Lavington, Xiaoxuan Liang +6
ICML 2024poster

Score function estimation is the cornerstone of both training and sampling from diffusion generative models. Despite this fact, the most commonly used estimators are either biased neural network approximations or high variance Monte Carlo estimators based on the conditional score. We introduce a nov…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

A Diffusion-Model of Joint Interactive Navigation

Matthew Niedoba, Jonathan Wilder Lavington, Yunpeng Liu, Vasileios Lioutas, Justice Sefas, Xiaoxuan Liang +5
NeurIPS 2023poster

Simulation of autonomous vehicle systems requires that simulated traffic participants exhibit diverse and realistic behaviors. The use of prerecorded real-world traffic scenarios in simulation ensures realism but the rarity of safety critical events makes large scale collection of driving scenarios…

Cited by 15Source ↗PDF ↗Scholar ↗
2023

Critic Sequential Monte Carlo

Vasileios Lioutas, Jonathan Wilder Lavington, Justice Sefas, Matthew Niedoba, Yunpeng Liu, Berend Zwartsenberg +3
ICLR 2023poster

We introduce CriticSMC, a new algorithm for planning as inference built from a composition of sequential Monte Carlo with learned Soft-Q function heuristic factors. These heuristic factors, obtained from parametric approximations of the marginal likelihood ahead, more effectively guide SMC towards t…

Cited by 9Source ↗PDF ↗Scholar ↗
2023

Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be

Frederik Kunstner, Jacques Chen, Jonathan Wilder Lavington, Mark Schmidt
ICLR 2023poster

The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoretical understanding of this discrepancy is lagging, preventing the development of significant improvements on either algo…

Cited by 72Source ↗PDF ↗code ↗Scholar ↗
2023

Target-based Surrogates for Stochastic Optimization

Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad Harikandeh, Mark Schmidt, Nicolas Le Roux
ICML 2023poster

We consider minimizing functions for which it is expensive to compute the (possibly stochastic) gradient. Such functions are prevalent in reinforcement learning, imitation learning and adversarial training. Our target optimization framework uses the (expensive) gradient computation to construct surr…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗