Kayhan Behdin

According to our database, Kayhan Behdin authored at least 22 papers between 2017 and 2025.

Collaborative distances:

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

2025

BP-Seg: A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation.

Fengyi Li, Kayhan Behdin, Natesh Pillai, Xiaofeng Wang, Zhipeng Wang, Ercan Yildiz

CoRR, May, 2025

An Optimization Framework for Differentially Private Sparse Fine-Tuning.

Mehdi Makni, Kayhan Behdin, Gabriel Afriat, Zheng Xu, Sergei Vassilvitskii, Natalia Ponomareva, Hussein Hazimeh, Rahul Mazumder

CoRR, March, 2025

Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications.

Kayhan Behdin, Yun Dai, Ata Fatahi Baarzi, Aman Gupta, Qingquan Song, Shao Tang, Hejian Sang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Maziar Sanjabi, Vignesh Kothapalli, Hamed Firooz, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Zhipeng Wang, Rahul Mazumder, Natesh Pillai, Luke Simon

CoRR, February, 2025

HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs.

Mehdi Makni, Kayhan Behdin, Zheng Xu, Natalia Ponomareva, Rahul Mazumder

CoRR, February, 2025

Efficient Algorithms for Leveraging LLMs for Generative and Predictive Recommender Systems.

Kayhan Behdin, Yun Dai, Gregory Dexter, Aman Gupta, Rahul Mazumder, Ankan Saha, Qingquan Song, Shao Tang, Sirou Zhu, Pin-Lun Hsu

Proceedings of the Companion Proceedings of the ACM on Web Conference 2025, 2025

A unified framework for Sparse plus Low-Rank Matrix Decomposition for LLMs.

Mehdi Makni, Kayhan Behdin, Zheng Xu, Natalia Ponomareva, Rahul Mazumder

Proceedings of the Conference on Parsimony and Learning, 2025

2024

Sparse NMF with Archetypal Regularization: Computational and Robustness Properties.

Kayhan Behdin, Rahul Mazumder

J. Mach. Learn. Res., 2024

ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models.

Xiang Meng, Kayhan Behdin, Haoyue Wang, Rahul Mazumder

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization.

Xiang Meng, Shibal Ibrahim, Kayhan Behdin, Hussein Hazimeh, Natalia Ponomareva, Rahul Mazumder

Proceedings of the Forty-first International Conference on Machine Learning, 2024

End-to-end Feature Selection Approach for Learning Skinny Trees.

Shibal Ibrahim, Kayhan Behdin, Rahul Mazumder

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

QuantEase: Optimization-based Quantization for Language Models - An Efficient and Intuitive Algorithm.

Kayhan Behdin, Ayan Acharya, Aman Gupta, Sathiya Keerthi Selvaraj, Rahul Mazumder

CoRR, 2023

Sparse Gaussian Graphical Models with Discrete Optimization: Computational and Statistical Perspectives.

Kayhan Behdin, Wenyu Chen, Rahul Mazumder

CoRR, 2023

Sharpness-Aware Minimization: An Implicit Regularization Perspective.

Kayhan Behdin, Rahul Mazumder

CoRR, 2023

mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization.

Kayhan Behdin, Qingquan Song, Aman Gupta, Ayan Acharya, David Durfee, Borja Ocejo, S. Sathiya Keerthi, Rahul Mazumder

CoRR, 2023

GRAND-SLAMIN' Interpretable Additive Modeling with Structural Constraints.

Shibal Ibrahim, Gabriel Afriat, Kayhan Behdin, Rahul Mazumder

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

2022

Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization.

Kayhan Behdin, Qingquan Song, Aman Gupta, David Durfee, Ayan Acharya, S. Sathiya Keerthi, Rahul Mazumder

CoRR, 2022

2021

Archetypal Analysis for Sparse Nonnegative Matrix Factorization: Robustness Under Misspecification.

Kayhan Behdin, Rahul Mazumder

CoRR, 2021

2020

Missing Low-Rank and Sparse Decomposition Based on Smoothed Nuclear Norm.

Masoumeh Azghani, Ashkan Esmaeili, Kayhan Behdin, Farokh Marvasti

IEEE Trans. Circuits Syst. Video Technol., 2020

Transductive multi-label learning from missing data using smoothed rank function.

Ashkan Esmaeili, Kayhan Behdin, Mohammad Amin Fakharian, Farokh Marvasti

Pattern Anal. Appl., 2020

2018

Recovering Quantized Data with Missing Information Using Bilinear Factorization and Augmented Lagrangian Method.

Ashkan Esmaeili, Kayhan Behdin, Sina Al-E.-Mohammad, Farokh Marvasti

CoRR, 2018

Transduction with Matrix Completion Using Smoothed Rank Function.

Ashkan Esmaeili, Kayhan Behdin, Mohammad Amin Fakharian, Farokh Marvasti

CoRR, 2018

2017

OBTAIN: Real-Time Beat Tracking in Audio Signals.

Ali Mottaghi, Kayhan Behdin, Ashkan Esmaeili, Mohammadreza Heydari, Farrokh Marvasti

CoRR, 2017