Alert button
Picture for Vahid Partovi Nia

Vahid Partovi Nia

Alert button

Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models

Dec 15, 2023
Alireza Ghaffari, Justin Yu, Mahsa Ghazvini Nejad, Masoud Asgharian, Boxing Chen, Vahid Partovi Nia

Viaarxiv icon

Mathematical Challenges in Deep Learning

Mar 24, 2023
Vahid Partovi Nia, Guojun Zhang, Ivan Kobyzev, Michael R. Metel, Xinlin Li, Ke Sun, Sobhan Hemati, Masoud Asgharian, Linglong Kong, Wulong Liu, Boxing Chen

Figure 1 for Mathematical Challenges in Deep Learning
Figure 2 for Mathematical Challenges in Deep Learning
Figure 3 for Mathematical Challenges in Deep Learning
Figure 4 for Mathematical Challenges in Deep Learning
Viaarxiv icon

Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm

Jan 17, 2023
Dounia Lakhmiri, Mahdi Zolnouri, Vahid Partovi Nia, Christophe Tribes, Sébastien Le Digabel

Figure 1 for Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm
Figure 2 for Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm
Figure 3 for Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm
Viaarxiv icon

On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats

Jan 09, 2023
Matteo Cacciola, Antonio Frangioni, Masoud Asgharian, Alireza Ghaffari, Vahid Partovi Nia

Figure 1 for On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats
Figure 2 for On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats
Figure 3 for On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats
Figure 4 for On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats
Viaarxiv icon

EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models

Dec 22, 2022
Xinlin Li, Mariana Parazeres, Adam Oberman, Alireza Ghaffari, Masoud Asgharian, Vahid Partovi Nia

Figure 1 for EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
Figure 2 for EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
Figure 3 for EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
Figure 4 for EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
Viaarxiv icon

Training Integer-Only Deep Recurrent Neural Networks

Dec 22, 2022
Vahid Partovi Nia, Eyyüb Sari, Vanessa Courville, Masoud Asgharian

Figure 1 for Training Integer-Only Deep Recurrent Neural Networks
Figure 2 for Training Integer-Only Deep Recurrent Neural Networks
Figure 3 for Training Integer-Only Deep Recurrent Neural Networks
Figure 4 for Training Integer-Only Deep Recurrent Neural Networks
Viaarxiv icon

KronA: Parameter Efficient Tuning with Kronecker Adapter

Dec 20, 2022
Ali Edalati, Marzieh Tahaei, Ivan Kobyzev, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh

Figure 1 for KronA: Parameter Efficient Tuning with Kronecker Adapter
Figure 2 for KronA: Parameter Efficient Tuning with Kronecker Adapter
Figure 3 for KronA: Parameter Efficient Tuning with Kronecker Adapter
Figure 4 for KronA: Parameter Efficient Tuning with Kronecker Adapter
Viaarxiv icon

SeKron: A Decomposition Method Supporting Many Factorization Structures

Oct 12, 2022
Marawan Gamal Abdel Hameed, Ali Mosleh, Marzieh S. Tahaei, Vahid Partovi Nia

Figure 1 for SeKron: A Decomposition Method Supporting Many Factorization Structures
Figure 2 for SeKron: A Decomposition Method Supporting Many Factorization Structures
Figure 3 for SeKron: A Decomposition Method Supporting Many Factorization Structures
Figure 4 for SeKron: A Decomposition Method Supporting Many Factorization Structures
Viaarxiv icon

Integer Fine-tuning of Transformer-based Models

Sep 20, 2022
Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia

Figure 1 for Integer Fine-tuning of Transformer-based Models
Figure 2 for Integer Fine-tuning of Transformer-based Models
Figure 3 for Integer Fine-tuning of Transformer-based Models
Figure 4 for Integer Fine-tuning of Transformer-based Models
Viaarxiv icon

DenseShift: Towards Accurate and Transferable Low-Bit Shift Network

Aug 20, 2022
Xinlin Li, Bang Liu, Rui Heng Yang, Vanessa Courville, Chao Xing, Vahid Partovi Nia

Figure 1 for DenseShift: Towards Accurate and Transferable Low-Bit Shift Network
Figure 2 for DenseShift: Towards Accurate and Transferable Low-Bit Shift Network
Figure 3 for DenseShift: Towards Accurate and Transferable Low-Bit Shift Network
Figure 4 for DenseShift: Towards Accurate and Transferable Low-Bit Shift Network
Viaarxiv icon