Amin Ghiasi

According to our database, Amin Ghiasi authored at least 14 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Improving Robustness with Adaptive Weight Decay.

Amin Ghiasi, Ali Shafahi, Reza Ardekani

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

What do Vision Transformers Learn? A Visual Exploration.

Amin Ghiasi, Hamid Kazemi, Eitan Borgnia, Steven Reich, Manli Shu, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein

CoRR, 2022

Adaptive Weight Decay: On The Fly Weight Decay Tuning for Improving Robustness.

Amin Ghiasi, Ali Shafahi, Reza Ardekani

CoRR, 2022

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations.

Amin Ghiasi, Hamid Kazemi, Steven Reich, Chen Zhu, Micah Goldblum, Tom Goldstein

Proceedings of the International Conference on Machine Learning, 2022

The Uncanny Similarity of Recurrence and Depth.

Avi Schwarzschild, Arjun Gupta, Amin Ghiasi, Micah Goldblum, Tom Goldstein

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations.

Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, Tom Goldstein

CoRR, 2021

Approximate Competitive Equilibrium with Generic Budget.

Amin Ghiasi, Masoud Seddighin

Proceedings of the Algorithmic Game Theory - 14th International Symposium, 2021

Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff.

Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Arjun Gupta

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer.

Chen Zhu, Zheng Xu, Ali Shafahi, Manli Shu, Amin Ghiasi, Tom Goldstein

CoRR, 2020

Adversarially robust transfer learning.

Ali Shafahi, Parsa Saadatpanah, Chen Zhu, Amin Ghiasi, Christoph Studer, David W. Jacobs, Tom Goldstein

Proceedings of the 8th International Conference on Learning Representations, 2020

Breaking Certified Defenses: Semantic Adversarial Examples with Spoofed robustness Certificates.

Amin Ghiasi, Ali Shafahi, Tom Goldstein

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?

Ali Shafahi, Amin Ghiasi, Furong Huang, Tom Goldstein

CoRR, 2019

Adversarial training for free!

Ali Shafahi, Mahyar Najibi, Amin Ghiasi, Zheng Xu, John P. Dickerson, Christoph Studer, Larry S. Davis, Gavin Taylor, Tom Goldstein

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Batch-wise Logit-Similarity: Generalizing Logit-Squeezing and Label-Smoothing.

Ali Shafahi, Amin Ghiasi, Mahyar Najibi, Furong Huang, John P. Dickerson, Tom Goldstein

Proceedings of the 30th British Machine Vision Conference 2019, 2019