Amir Gholami

3.9k citations
23 papers · 1.0k indexed · 1 hit paper · h-index 11

Amir Gholami

22 papers receiving 1.0k citations

Hit Papers

Q-BERT: Hessian Based Ultra Low Precision Quantization of...223202020262022202450100150200

Peers

Amir Gholami
Comparison fields: 5 of 85
  • Computer Vision and Pattern Recognition 591
  • Artificial Intelligence 657
  • Computational Mathematics 11
  • Hardware and Architecture 44
  • Neurology 38
Replace Rohan Varma with:
Rohan Varma United States
Shan You China
Levent Sagun United States
Jungwook Choi South Korea
Ankur Agrawal United States
Liangzhen Lai United States
Nan Jiang China
Mingyu Yan China
Ioannis Mitliagkas United States
Amir Gholami relative to Rohan Varma United States Rohan Varma's profile →
Citations per field
00.5×2.9×
Rohan Varma · 1×
Citations per year

Countries citing papers authored by Amir Gholami

Since Specialization
Citations

This map shows the geographic impact of Amir Gholami's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Amir Gholami with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Amir Gholami more than expected).

Fields of papers citing papers by Amir Gholami

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Amir Gholami. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Amir Gholami. The network helps show where Amir Gholami may publish in the future.

Co-authorship network

The 25 scholars most cited alongside Amir Gholami, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Amir Gholami Line = papers co-authored together Amir Gholami links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown
#Work
1 20250
2 20247
3 20241
4 20244
5 20228
6 202249
7 202222
8 202188
9 2020195
10 202065
11 20208
12
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERTbreakdown →
2020223
13 201928
14 2019224
15
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
20188
16 201840
17 201818
18 20186
19
Integrated Model and Data Parallelism in Training Neural Networks.
20173
20
FFT, FMM, or MULTIGRID? A comparative study of state-of-the-art poisson solvers.
20142

About Amir Gholami

Amir Gholami is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Hardware and Architecture, having authored 23 papers that have together received 1.0k indexed citations. Recurring topics across this work include Advanced Neural Network Applications (13 papers), Stochastic Gradient Optimization Techniques (5 papers), Domain Adaptation and Few-Shot Learning (5 papers), Adversarial Robustness in Machine Learning (3 papers), Parallel Computing and Optimization Techniques (3 papers), Natural Language Processing Techniques (3 papers), CCD and CMOS Imaging Sensors (2 papers) and Machine Learning and ELM (2 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (591 citations), Artificial Intelligence (657 citations) and Computational Mathematics (11 citations). Amir Gholami has collaborated with scholars based in United States, China and South Korea. Frequent co-authors include Kurt Keutzer, Michael W. Mahoney, Zhewei Yao, Zhen Dong, Sheng Shen, Yaohui Cai, Jiayu Ye, Linjian Ma, Zhen Dong and Mustafa Mustafa. Their work appears in journals such as Journal of Mathematical Biology, arXiv (Cornell University) and eScholarship (California Digital Library).

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026