Follow
Roman Novak
Roman Novak
Google Brain
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Deep Neural Networks as Gaussian Processes
J Lee, Y Bahri, R Novak, SS Schoenholz, J Pennington, J Sohl-Dickstein
International Conference on Learning Representations (ICLR) 2018, 2017
11332017
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
J Lee, L Xiao, SS Schoenholz, Y Bahri, R Novak, J Sohl-Dickstein, ...
Advances in Neural Information Processing Systems (NeurIPS) 32, 8570 - 8581, 2019
9792019
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ...
arXiv preprint arXiv:2206.04615, 2022
6932022
Sensitivity and Generalization in Neural Networks: an Empirical Study
R Novak, Y Bahri, DA Abolafia, J Pennington, J Sohl-Dickstein
International Conference on Learning Representations (ICLR) 2018, 2018
4582018
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
R Novak, L Xiao, J Lee, Y Bahri, G Yang, J Hron, D Abolafia, J Pennington, ...
International Conference on Learning Representations (ICLR) 2019, 2018
3312018
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
R Novak, L Xiao, J Hron, J Lee, AA Alemi, J Sohl-Dickstein, ...
International Conference on Learning Representations (ICLR) 2020, 2019
2312019
Finite versus infinite neural networks: an empirical study
J Lee, SS Schoenholz, J Pennington, B Adlam, L Xiao, R Novak, ...
Neural Information Processing Systems (NeurIPS) 2020, 2020
1782020
Dataset Distillation with Infinitely Wide Convolutional Networks
T Nguyen, R Novak, L Xiao, J Lee
Neural Information Processing Systems (NeurIPS) 2021, 2021
1762021
Infinite attention: NNGP and NTK for deep attention networks
J Hron, Y Bahri, J Sohl-Dickstein, R Novak
International Conference on Machine Learning (ICML) 2020, 2020
1022020
On the infinite width limit of neural networks with a standard parameterization
J Sohl-Dickstein, R Novak, SS Schoenholz, J Lee
arXiv preprint arXiv:2001.07301, 2020
482020
Fast finite width neural tangent kernel
R Novak, J Sohl-Dickstein, SS Schoenholz
International Conference on Machine Learning (ICML) 2022, 2021
472021
Improving the Neural Algorithm of Artistic Style
R Novak, Y Nikulin
arXiv preprint arXiv:1605.04603, 2016
302016
Exploring the Neural Algorithm of Artistic Style
Y Nikulin, R Novak
arXiv preprint arXiv:1602.07188, 2016
302016
Iterative Refinement for Machine Translation
R Novak, M Auli, D Grangier
Bay Area Machine Learning Symposium (BayLearn) 2017, 2016
292016
Exact posterior distributions of wide Bayesian neural networks
J Hron, Y Bahri, R Novak, J Pennington, J Sohl-Dickstein
ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning; BayLearn 2020, 2020
282020
Beyond human data: Scaling self-training for problem-solving with language models
A Singh, JD Co-Reyes, R Agarwal, A Anand, P Patil, PJ Liu, J Harrison, ...
arXiv preprint arXiv:2312.06585, 2023
172023
Fast Neural Kernel Embeddings for General Activations
I Han, A Zandieh, J Lee, R Novak, L Xiao, A Karbasi
Neural Information Processing Systems (NeurIPS) 2022, 2022
112022
Small-scale proxies for large-scale transformer training instabilities
M Wortsman, PJ Liu, L Xiao, K Everett, A Alemi, B Adlam, JD Co-Reyes, ...
arXiv preprint arXiv:2309.14322, 2023
62023
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
J Hron, R Novak, J Pennington, J Sohl-Dickstein
International Conference on Machine Learning (ICML) 2022, 2022
52022
Frontier Language Models are not Robust to Adversarial Arithmetic, or" What do I need to say so you agree 2+ 2= 5?
CD Freeman, L Culp, A Parisi, ML Bileschi, GF Elsayed, A Rizkowsky, ...
arXiv preprint arXiv:2311.07587, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–20