Følg
Jonathan Wilder Lavington
Titel
Citeret af
Citeret af
År
Noise is not the main factor behind the gap between sgd and adam on transformers, but sign descent might be
F Kunstner, J Chen, JW Lavington, M Schmidt
arXiv preprint arXiv:2304.13960, 2023
602023
Robust Asymmetric Learning in POMDPs
A Warrington, JW Lavington, A Scibior, M Schmidt, F Wood
International Conference on Machine Learning, 11013-11023, 2021
352021
A diffusion-model of joint interactive navigation
M Niedoba, J Lavington, Y Liu, V Lioutas, J Sefas, X Liang, D Green, ...
Advances in Neural Information Processing Systems 36, 2024
102024
Target-based Surrogates for Stochastic Optimization
J Wilder Lavington, S Vaswani, R Babanezhad, M Schmidt, N Le Roux
arXiv e-prints, arXiv: 2302.02607, 2023
8*2023
Conditional permutation invariant flows
B Zwartsenberg, A Ścibior, M Niedoba, V Lioutas, Y Liu, J Sefas, S Dabiri, ...
arXiv preprint arXiv:2206.09021, 2022
82022
Critic sequential monte carlo
V Lioutas, JW Lavington, J Sefas, M Niedoba, Y Liu, B Zwartsenberg, ...
arXiv preprint arXiv:2205.15460, 2022
72022
Heavy-tailed noise does not explain the gap between SGD and Adam, but sign descent might
F Kunstner, J Chen, JW Lavington, M Schmidt
International Conference on Learning Representations, 5, 2023
62023
Improved policy optimization for online imitation learning
JW Lavington, S Vaswani, M Schmidt
Conference on Lifelong Learning Agents, 1146-1173, 2022
62022
TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characters
JW Lavington, K Zhang, V Lioutas, M Niedoba, Y Liu, D Green, ...
arXiv preprint arXiv:2405.04491, 2024
32024
A Closer Look at Gradient Estimators with Reinforcement Learning as Inference
JW Lavington, M Teng, M Schmidt, F Wood
Deep RL Workshop NeurIPS 2021, 2021
32021
A Probabilistic Modeling Approach to CRISPR-Cas9
JW Lavington
University of Colorado at Boulder, 2018
22018
Semantically Consistent Video Inpainting with Conditional Diffusion Models
D Green, W Harvey, S Naderiparizi, M Niedoba, Y Liu, X Liang, ...
arXiv preprint arXiv:2405.00251, 2024
12024
Nearest Neighbour Score Estimators for Diffusion Generative Models
M Niedoba, D Green, S Naderiparizi, V Lioutas, JW Lavington, X Liang, ...
arXiv preprint arXiv:2402.08018, 2024
12024
Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm
AV Ramesh, A Mishkin, M Schmidt, Y Zhou, JW Lavington, J She
arXiv preprint arXiv:2307.01169, 2023
12023
Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models
S Dabiri, V Lioutas, B Zwartsenberg, Y Liu, M Niedoba, X Liang, D Green, ...
arXiv preprint arXiv:2305.14621, 2023
12023
Vehicle type specific waypoint generation
Y Liu, JW Lavington, A Scibior, F Wood
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2022
12022
An Empirical Study of Non-Uniform Sampling in Off-Policy Reinforcement Learning for Continuous Control
N Ioannidis, JW Lavington, M Schmidt
Deep RL Workshop NeurIPS 2021, 2021
12021
Taking advantage of common assumptions in policy optimization and reinforcement learning
JW Lavington
University of British Columbia, 2024
2024
Video Killed the HD-Map: Predicting Multi-Agent Behavior Directly From Aerial Images
Y Liu, V Lioutas, JW Lavington, M Niedoba, J Sefas, S Dabiri, D Green, ...
2023 IEEE 26th International Conference on Intelligent Transportation …, 2023
2023
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–19