Elad Hoffer
Scholar

Elad Hoffer

Google Scholar ID: iEfTH7AAAAAJ
PhD, Research
Deep LearningMachine LearningArtificial Intelligence
Citations & Impact
All-time
Citations
6,049
 
H-index
18
 
i10-index
18
 
Publications
20
 
Co-authors
25
list available
Resume (English only)
Academic Achievements
  • Publications:
  • - Neural gradients are near-lognormal: improved quantized and sparse training, ICLR 2021
  • - Task-agnostic continual learning using online variational bayes with fixed-point updates, Neural Computation 2021
  • - Increasing batch size through instance repetition improves generalization, CVPR 2020
  • - The Knowledge Within: Methods for Data-Free Model Compression, CVPR 2020
  • - At Stability’s Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?, ICLR 2020, Spotlight
  • - Norm matters: efficient and accurate normalization schemes in deep networks, NeurIPS 2018, Spotlight
  • - Scalable Methods for 8-bit Training of Neural Networks, NeurIPS 2018
  • - Fix your classifier: the marginal value of training the last weight layer, ICLR 2018
  • - The Implicit Bias of Gradient Descent on Separable Data, ICLR 2018
  • - Exponentially vanishing sub-optimal local minima in multilayer neural networks, ICLR 2018 - workshop
  • - Train longer, generalize better: closing the generalization gap in large batch training of neural networks, NIPS 2017, Oral presentation
  • - Semi-supervised deep learning by metric embedding, ICLR 2017 - workshop
  • - Spatial contrasting for deep unsupervised learning, NIPS 2016 - Workshop
  • - Deep metric learning using Triplet network, ICLR 2015
  • Patents: IMAGE DIFFERENCE BASED SEGMENTATION USING RECURSIVE NEURAL NETWORKS, Patent US20180227483A1
Research Experience
  • Current research focuses on deep learning representations and other related topics in machine learning and computer vision.
Education
  • Ph.D. (2019): Electrical Engineering, Technion - Israel Institute of Technology, Advisors: Prof. Daniel Soudry and Prof. Nir Ailon; M.Sc. (2016): Electrical Engineering, Technion - Israel Institute of Technology; B.Sc. (2014): Electrical Engineering, Technion - Israel Institute of Technology.
Background
  • Research Interests: Deep Learning, Machine Learning, and Computer Vision. Professional Field: Electrical Engineering.