Yasaman Bahri

Research Scientist, Brain.

Research Areas

Authored Publications
0 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
Explaining Neural Scaling Laws
Ethan S Dyer
Jaehoon Lee
Jared D Kaplan
Utkarsh Sharma
Yasaman Bahri
arxiv (2021)
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
Anders Andreassen
Yasaman Bahri
Behnam Neyshabur
Rebecca Roelofs
arXiv (2021)
The large learning rate phase of deep learning
Aitor Lewkowycz
Ethan S Dyer
Guy Gur-Ari
Jascha Sohl-dickstein
Yasaman Bahri
arxiv (2020)
Infinite attention: NNGP and NTK for deep attention networks
Jiri Hron
Yasaman Bahri
Jascha Sohl-dickstein
Roman Novak
International Conference on Machine Learning 2020 (2020) (to appear)
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
Roman Novak
Lechao Xiao
Jaehoon Lee
Yasaman Bahri
Greg Yang
Jiri Hron
Dan Abolafia
Jeffrey Pennington
Jascha Sohl-dickstein
ICLR (2019)
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
Jaehoon Lee
Lechao Xiao
Sam Schoenholz
Yasaman Bahri
Roman Novak
Jascha Sohl-dickstein
Jeffrey Pennington
NeurIPS (2019)
Deep Neural Networks as Gaussian Processes
Jaehoon Lee
Yasaman Bahri
Roman Novak
Sam Schoenholz
Jeffrey Pennington
Jascha Sohl-dickstein
ICLR (2018)
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
Lechao Xiao
Yasaman Bahri
Jascha Sohl-dickstein
Sam Schoenholz
Jeffrey Pennington
ICML (2018)
Sensitivity and Generalization in Neural Networks: an Empirical Study
Roman Novak
Yasaman Bahri
Dan Abolafia
Jeffrey Pennington
Jascha Sohl-dickstein
ICLR (2018)
Training ultra-deep CNNs with critical initialization
Lechao Xiao
Yasaman Bahri
Sam Schoenholz
Jeffrey Pennington
NIPS Workshop (2017)
Search on Google Scholar