Alert button
Picture for Vivek Ramanujan

Vivek Ramanujan

Alert button

Parameter Norm Growth During Training of Transformers

Oct 19, 2020
William Merrill, Vivek Ramanujan, Yoav Goldberg, Roy Schwartz, Noah Smith

Figure 1 for Parameter Norm Growth During Training of Transformers
Figure 2 for Parameter Norm Growth During Training of Transformers
Figure 3 for Parameter Norm Growth During Training of Transformers
Figure 4 for Parameter Norm Growth During Training of Transformers
Viaarxiv icon

Supermasks in Superposition

Jun 30, 2020
Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu, Aniruddha Kembhavi, Mohammad Rastegari, Jason Yosinski, Ali Farhadi

Figure 1 for Supermasks in Superposition
Figure 2 for Supermasks in Superposition
Figure 3 for Supermasks in Superposition
Figure 4 for Supermasks in Superposition
Viaarxiv icon

Soft Threshold Weight Reparameterization for Learnable Sparsity

Mar 11, 2020
Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham Kakade, Ali Farhadi

Figure 1 for Soft Threshold Weight Reparameterization for Learnable Sparsity
Figure 2 for Soft Threshold Weight Reparameterization for Learnable Sparsity
Figure 3 for Soft Threshold Weight Reparameterization for Learnable Sparsity
Figure 4 for Soft Threshold Weight Reparameterization for Learnable Sparsity
Viaarxiv icon

What's Hidden in a Randomly Weighted Neural Network?

Nov 29, 2019
Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari

Figure 1 for What's Hidden in a Randomly Weighted Neural Network?
Figure 2 for What's Hidden in a Randomly Weighted Neural Network?
Figure 3 for What's Hidden in a Randomly Weighted Neural Network?
Figure 4 for What's Hidden in a Randomly Weighted Neural Network?
Viaarxiv icon

Improving Shape Deformation in Unsupervised Image-to-Image Translation

Aug 13, 2018
Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin

Figure 1 for Improving Shape Deformation in Unsupervised Image-to-Image Translation
Figure 2 for Improving Shape Deformation in Unsupervised Image-to-Image Translation
Figure 3 for Improving Shape Deformation in Unsupervised Image-to-Image Translation
Figure 4 for Improving Shape Deformation in Unsupervised Image-to-Image Translation
Viaarxiv icon