Hanie Sedghi

Hanie Sedghi

I am a senior research scientist at Brain team. My approach is to bond theory and practice in large-scale machine learning. Over the recent years. I have been working on understanding deep learning phenomena and improving the training algorithms. I lead the DeepPhenomena team at Google.

Webpage

Twitter:@HanieSedghi

Research Areas

Authored Publications
0 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
Exploring the Limits of Large Scale Pre-training
Samira Abnar
Mostafa Dehghani
Behnam Neyshabur
Hanie Sedghi
ICLR Spotlight (2022)
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Saurabh Garg
Sivaraman Balakrishnan
Zachary Chase Lipton
Behnam Neyshabur
Hanie Sedghi
ICLR (2022)
The role of permutation invariance in linear mode connectivity of neural networks
Rahim Entezari
Hanie Sedghi
Olga Saukh
Behnam Neyshabur
ICLR (2022)
Avoiding Spurious Correlations: Bridging Theory and Practice
Thao Nguyen
Vaishnavh Nagarajan
Hanie Sedghi
Behnam Neyshabur
NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications
The Deep Bootstrap: Good Online Learners are Good Offline Generalizers
Preetum Nakkiran
Behnam Neyshabur
Hanie Sedghi
ICLR (2021)
Generalization bounds for deep convolutional neural networks
Phil Long
Hanie Sedghi
ICLR (2020)
What is being transferred in transfer learning?
Behnam Neyshabur
Hanie Sedghi
Chiyuan Zhang
NeurIPS (2020)
The intriguing role of module criticality in the generalization of deep networks
Niladri Chatterji
Behnam Neyshabur
Hanie Sedghi
ICLR Spotlight (2020)
The Singular Values of Convolutional Layers
Hanie Sedghi
Phil Long
Vineet Gupta
ICLR (2019)
On the effect of the activation function on the distribution of hidden nodes in a deep network
Phil Long
Hanie Sedghi
Neural Computation, 31 (2019), pp. 2562-2580
Search on Google Scholar