Follow
Kayhan Behdin
Kayhan Behdin
LinkedIn
Verified email at mit.edu - Homepage
Title
Cited by
Cited by
Year
Improved deep neural network generalization using m-sharpness-aware minimization
K Behdin, Q Song, A Gupta, D Durfee, A Acharya, S Keerthi, R Mazumder
arXiv preprint arXiv:2212.04343, 2022
15*2022
Transductive multi-label learning from missing data using smoothed rank function
A Esmaeili, K Behdin, MA Fakharian, F Marvasti
Pattern Analysis and Applications 23 (3), 1225-1233, 2020
15*2020
Missing low-rank and sparse decomposition based on smoothed nuclear norm
M Azghani, A Esmaeili, K Behdin, F Marvasti
IEEE Transactions on Circuits and Systems for Video Technology 30 (6), 1550-1558, 2019
132019
OBTAIN: Real-Time Beat Tracking in Audio Signals
A Mottaghi, K Behdin, A Esmaeili, M Heydari, F Marvasti
ICOSP 2017, The workshop of ICCSIT 2017, Florence, Italy, 2017
132017
QuantEase: Optimization-based Quantization for Language Models
K Behdin, A Acharya, A Gupta, Q Song, S Zhu, S Keerthi, R Mazumder
arXiv e-prints, arXiv: 2309.01885, 2023
12*2023
On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees
K Behdin, R Mazumder
arXiv preprint arXiv:2302.11836, 2023
12*2023
Sparse PCA: A new scalable estimator based on integer programming
K Behdin, R Mazumder
arXiv preprint arXiv:2109.11142, 2021
72021
OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
X Meng, S Ibrahim, K Behdin, H Hazimeh, N Ponomareva, R Mazumder
arXiv preprint arXiv:2403.12983, 2024
52024
GRAND-SLAMIN’Interpretable Additive Modeling with Structural Constraints
S Ibrahim, G Afriat, K Behdin, R Mazumder
Advances in Neural Information Processing Systems 36, 2024
42024
ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
X Meng, K Behdin, H Wang, R Mazumder
arXiv preprint arXiv:2406.07831, 2024
32024
Sparse NMF with Archetypal Regularization: Computational and Robustness Properties
K Behdin, R Mazumder
Journal of Machine Learning Research 25, 2024
3*2024
Sparse Gaussian Graphical Models with Discrete Optimization: Computational and Statistical Perspectives
K Behdin, W Chen, R Mazumder
arXiv preprint arXiv:2307.09366, 2023
32023
Recovering quantized data with missing information using bilinear factorization and augmented Lagrangian method
A Esmaeili, K Behdin, F Marvasti
arXiv preprint arXiv:1810.03222, 2018
32018
End-to-end Feature Selection Approach for Learning Skinny Trees
S Ibrahim, K Behdin, R Mazumder
International Conference on Artificial Intelligence and Statistics, 2863-2871, 2024
12024
Differentially Private Best Subset Selection Via Integer Programming
K Behdin, P Prastakos, R Mazumder
Privacy Regulation and Protection in Machine Learning, 2024
2024
Statistical Learning with Discrete Structures: Statistical and Computational Perspectives
K Behdin
Massachusetts Institute of Technology, 2024
2024
Multi-Task Learning for Sparsity Pattern Heterogeneity: A Discrete Optimization Approach
G Loewinger, K Behdin, KT Kishida, G Parmigiani, R Mazumder
arXiv preprint arXiv:2212.08697, 2022
2022
Multi-Task Learning for Sparsity Pattern Heterogeneity: Statistical and Computational Perspectives
K Behdin, G Loewinger, KT Kishida, G Parmigiani, R Mazumder
arXiv e-prints, arXiv: 2212.08697, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–18