Следене
Dami Choi
Dami Choi
Потвърден имейл адрес: cs.toronto.edu - Начална страница
Заглавие
Позовавания
Позовавания
Година
On empirical comparisons of optimizers for deep learning
D Choi
arXiv preprint arXiv:1910.05446, 2019
4092019
Backpropagation through the void: Optimizing control variates for black-box gradient estimation
W Grathwohl, D Choi, Y Wu, G Roeder, D Duvenaud
arXiv preprint arXiv:1711.00123, 2017
3312017
Guided evolutionary strategies: Augmenting random search with surrogate gradients
N Maheswaranathan, L Metz, G Tucker, D Choi, J Sohl-Dickstein
International Conference on Machine Learning, 4264-4273, 2019
1012019
Gradient estimation with stochastic softmax tricks
M Paulus, D Choi, D Tarlow, A Krause, CJ Maddison
Advances in neural information processing systems 33, 5691-5704, 2020
872020
Faster neural network training with data echoing
D Choi, A Passos, CJ Shallue, GE Dahl
arXiv preprint arXiv:1907.05550, 2019
562019
Guided evolutionary strategies: escaping the curse of dimensionality in random search
N Maheswaranathan, L Metz, G Tucker, D Choi, J Sohl-Dickstein
212018
Tools for verifying neural models' training data
D Choi, Y Shavit, DK Duvenaud
Advances in Neural Information Processing Systems 36, 2024
102024
On empirical comparisons of optimizers for deep learning: arXiv preprint, doi: 10. 48550
D Choi, CJ Shallue, Z Nado, J Lee, CJ Maddison, GE Dahl
arxiv, 1910
101910
Self-tuning stochastic optimization with curvature-aware gradient filtering
RTQ Chen, D Choi, L Balles, D Duvenaud, P Hennig
PMLR, 2020
92020
Connecting the dots: Llms can infer and verbalize latent structure from disparate training data
J Treutlein, D Choi, J Betley, S Marks, C Anil, R Grosse, O Evans
arXiv preprint arXiv:2406.14546, 2024
82024
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
J Requeima, J Bronskill, D Choi, RE Turner, D Duvenaud
arXiv preprint arXiv:2405.12856, 2024
72024
Order matters in the presence of dataset imbalance for multilingual learning
D Choi, D Xin, H Dadkhahi, J Gilmer, A Garg, O Firat, CK Yeh, AM Dai, ...
Advances in Neural Information Processing Systems 36, 2024
52024
Systems and methods for reducing idleness in a machine-learning training system using data echoing
D Choi, AT Passos, CJ Shallue, GE Dahl
US Patent 11,537,949, 2022
2022
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–13