Volgen
Hattie Zhou
Hattie Zhou
Mila; Université de Montréal
Geverifieerd e-mailadres voor mila.quebec - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Deconstructing lottery tickets: Zeros, signs, and the supermask
H Zhou, J Lan, R Liu, J Yosinski
Advances in neural information processing systems 32, 2019
4222019
Teaching algorithmic reasoning via in-context learning
H Zhou, A Nova, H Larochelle, A Courville, B Neyshabur, H Sedghi
arXiv preprint arXiv:2211.09066, 2022
72*2022
Fortuitous forgetting in connectionist networks
H Zhou, A Vani, H Larochelle, A Courville
International Conference on Learning Representations, 2021
252021
Lca: Loss change allocation for neural network training
J Lan, R Liu, H Zhou, J Yosinski
Advances in Neural Information Processing Systems 32, 2019
252019
What algorithms can transformers learn? a study in length generalization
H Zhou, A Bradley, E Littwin, N Razin, O Saremi, J Susskind, S Bengio, ...
arXiv preprint arXiv:2310.16028, 2023
212023
Predicting grokking long before it happens: A look into the loss landscape of models which grok
P Notsawo Jr, H Zhou, M Pezeshki, I Rish, G Dumas
arXiv preprint arXiv:2306.13253, 2023
62023
Vanishing gradients in reinforcement finetuning of language models
N Razin, H Zhou, O Saremi, V Thilak, A Bradley, P Nakkiran, J Susskind, ...
arXiv preprint arXiv:2310.20703, 2023
12023
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–7