Vahid Partovi Nia

Adjunct Professor, Mathematics and Industrial Engineering, École Polytechnique de Montréal, Université de Montréal

Joined

September 2019

Names

Vahid Partovi Nia (Preferred)

Emails

****@huawei.com (Confirmed)

****@polymtl.ca (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Adjunct Professor

Mathematics and Industrial Engineering, École Polytechnique de Montréal, Université de Montréal (polymtl.ca)

2017 – Present

Advisors, Relations & Conflicts

Postdoc Advisor

David Stephens

2009 – 2011

Postdoc Advisor

Masoud Asgharian

2009 – 2011

PhD Advisor

Anthony Davison

2006 – 2009

Expertise

Neural Compression: Quantization

Pruning

Decomposition

2017 – 2023

Causal Inference

2017 – 2022

Bayesian Supervised and Unsupervised Learning

2005 – 2017

Publications

A convergence diagnostic for Bayesian clustering
Martin Lysy, Masoud Asgharian, Vahid Partovi Nia
- WIREs Computational Statistics
- Readers: Everyone
A Causal Direction Test for Heterogeneous Populations
Vahid Partovi Nia, Xinlin Li, Masoud Asgharian, Shoubo Hu, Yanhui Geng, Zhitang Chen
- Machine Learning with Applications
- Readers: Everyone
EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
Xinlin Li, Mariana Oliveira Prazeres, Adam Oberman, Alireza Ghaffari, Masoud Asgharian, Vahid Partovi Nia
- Springer Nature (SN) Computer Science
- Readers: Everyone
On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats
Matteo Cacciola, Antonio Frangioni, Masoud Asgharian, Alireza Ghaffari, Vahid Partovi Nia
- Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods
- Readers: Everyone
Training Integer-Only Deep Recurrent Neural Networks
Vahid Partovi Nia, Eyyub Sari, Vanessa Courville, Masoud Asgharian
- Springer Nature (SN) Computer Science
- Readers: Everyone
Towards fine-tuning pre-trained language models with integer forward and backward propagation
Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia
- Findings of the Association for Computational Linguistics: EACL 2023
- Readers: Everyone
Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models
Alireza Ghaffari, Justin Yu, Mahsa Ghazvini Nejad, Masoud Asgharian, Boxing Chen, Vahid Partovi Nia
- Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods
- Readers: Everyone
Partially Shared Query-Key for Lightweight Language Models
Kai Yang, Vahid Partovi Nia, Boxing Chen, Masoud Asgharian
- 4th NeurIPS Efficient Natural Language and Speech Processing Workshop (ENLSP-IV 2024).
- Readers: Everyone
AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs
Alireza Ghaffari, Sharareh Younesian, Vahid Partovi Nia, Boxing Chen, Masoud Asgharian
- OpenReview Archive Direct Upload
- Readers: Everyone
OAC: Output-adaptive Calibration for Accurate Post-training Quantization
Ali Edalati, Alireza Ghaffari, Mahsa Ghazvini Nejad, Lu Hou, Boxing Chen, Masoud Asgharian, Vahid Partovi Nia
- Proceedings of the AAAI Conference on Artificial Intelligence
- Readers: Everyone

View all 25 publications

Co-Authors

View all 49 co-authors