Yerlan Idelbayev

EECS PhD Student

I'm a 5th year PhD student (now candidate) supervised by Miguel Á. Carreira-Perpiñán at UC Merced . My current research interests lie in model compression, particularly compression of deep neural networks, e.g. quantization, pruning, etc.

Publications


An Empirical Comparison of Quantization, Pruning and Low-rank Neural Network Compression using the LC Toolkit
Idelbayev, Y. and Carreira-Perpiñán, M. Á.
To appear in IEEE International Joint Conference on Neural Networks (IJCNN 2021)
[external link][paper preprint][© IEEE]

Optimal Quantization using Scaled Codebook
Idelbayev, Y., Molchanov, P., Shen, M., Yin, H., Carreira-Perpiñán, M. Á. and Alvarez, J. M.
To appear in IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2021)
[external link][paper preprint][© IEEE]

Optimal Selection of Matrix Shape and Decomposition Scheme for Neural Network Compression
Idelbayev, Y. and Carreira-Perpiñán, M. Á.
To appear in IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2021)
[external link][paper preprint][code on github] [© IEEE]

Neural Network Compression via Additive Combination of Reshaped, Low-rank Matrices
Idelbayev, Y. and Carreira-Perpiñán, M. Á.
To appear in IEEE Data Compression Conference (DCC 2021)
[external link][paper preprint][code on github] [© IEEE]

A Flexible, Extensible Software Framework for Model Compression Based on the LC Algorithm
Idelbayev, Y. and Carreira-Perpiñán, M. Á. (2020)
Unpublished manuscript, May 15, 2020, arXiv:2005.07786
[external link][paper preprint][code on github]

Extended abstract at the Bay Area Machine Learning Symposium, Oct. 15, 2020 (BayLearn 2020)
[external link] [paper preprint] [slides]

Low-rank Compression of Neural Nets: Learning the Rank of Each Layer
Idelbayev, Y. and Carreira-Perpiñán, M. Á. (2020)
IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2020)
[external link][paper preprint][supplementary material] [code on github][short video][© IEEE]

Structured Multi-Hashing for Model Compression
Eban, E., Movshovitz-Attias,Y., Wu, H., Sandler, M., Poon, A., Idelbayev, Y. and Carreira-Perpiñán, M. Á. (2020)
IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2020)
[external link][arxiv][preprint][© IEEE]

"Learning-compression" Algorithms for Neural Net Pruning
Carreira-Perpiñán, M. Á. and Idelbayev, Y. (2018)
IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2018)
[external link] [paper preprint] [poster] [supplementary material] [Python implementation][spotlight] [© IEEE]

Model Compression as Constrained Optimization, with Application to Neural Nets. Part II: quantization
Carreira-Perpiñán, M. Á. and Idelbayev, Y . (2017)
Unpublished manuscript, Jul. 13, 2017, arXiv:1707.04319
[external link] [paper preprint] [code on github]


Short version at the Workshop on Optimization for Machine Learning (NIPS 2017)
[external link] [paper preprint] [poster]
Short version at the Workshop on Machine Learning on the Phone and other Consumer Devices (NIPS 2017)
[external link] [paper preprint] [poster]
Extended abstract at the Bay Area Machine Learning Symposium, Oct. 19, 2017 (BayLearn 2017)
[external link] [paper preprint] [slides] [video]

Small Molecule Accurate Recognition Technology (SMART) to Enhance Natural Products Research
Zhang, C., Idelbayev, Y., Roberts, N., Tao, Y., Nannapaneni, Y., Duggan, B., Min, J., Lin, E., Gerwick, E., Garrison W. Cottrell, G. and Gerwick, W.
Scientific Reports 7, 14243 (2017)
[external link] [paper] [CC BY 4.0]