Anastasios Kyrillidis
Anastasios Kyrillidis
Associate Professor, Computer Science Department, Ken Kennedy Institute Fellow, Rice University
Verified email at - Homepage
Cited by
Cited by
Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach
D Park, A Kyrillidis, C Caramanis, S Sanghavi
Artificial Intelligence and Statistics, pp. 65-74, 2016
Dropping convexity for faster semi-definite optimization
S Bhojanapalli, A Kyrillidis, S Sanghavi
Conference on Learning Theory, 530-582, 2016
Current progress and open challenges for applying deep learning across the biosciences
N Sapoval, A Aghazadeh, MG Nute, DA Antunes, A Balaji, R Baraniuk, ...
Nature Communications 13 (1), 1728, 2022
Multi-way compressed sensing for sparse low-rank tensors
ND Sidiropoulos, A Kyrillidis
IEEE Signal Processing Letters, 1-1, 2012
Finding low-rank solutions via non-convex matrix factorization, efficiently and provably
D Park, A Kyrillidis, C Caramanis, S Sanghavi
SIAM Journal on Imaging Sciences 11 (4), 2165–2204, 2018
Sparse projections onto the simplex
A Kyrillidis, S Becker, V Cevher, C Koch
Proceedings of The 30th International Conference on Machine Learning 28, 235–243, 2012
Composite self-concordant minimization.
Q Tran-Dinh, A Kyrillidis, V Cevher
J. Mach. Learn. Res. 16 (1), 371-416, 2015
Provable deterministic leverage score sampling
D Papailiopoulos, A Kyrillidis, C Boutsidis
Proceedings of the 20th ACM SIGKDD international conference on Knowledge …, 2014
Matrix recipes for hard thresholding methods
A Kyrillidis, V Cevher
Journal of Mathematical Imaging and Vision, 2012
Provable compressed sensing quantum state tomography via non-convex methods
A Kyrillidis, A Kalev, D Park, S Bhojanapalli, C Caramanis, S Sanghavi
npj Quantum Information 4 (1), 36, 2018
PipeGCN: Efficient full-graph training of graph convolutional networks with pipelined feature communication
C Wan, Y Li, CR Wolfe, A Kyrillidis, NS Kim, Y Lin
arXiv preprint arXiv:2203.10428, 2022
Recipes on hard thresholding methods
A Kyrillidis, V Cevher
2011 4th IEEE International Workshop on Computational Advances in Multi …, 2011
Statistical inference using SGD
T Li, L Liu, A Kyrillidis, C Caramanis
Thirty-Second AAAI Conference on Artificial Intelligence, 3571-3578, 2017
Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time
Z Liu, A Desai, F Liao, W Wang, V Xie, Z Xu, A Kyrillidis, A Shrivastava
Advances in Neural Information Processing Systems 36, 2024
Combinatorial selection and least absolute shrinkage via the CLASH algorithm
A Kyrillidis, V Cevher
2012 IEEE International Symposium on Information Theory Proceedings, 2216-2220, 2012
Distributed learning of fully connected neural networks using independent subnet training
B Yuan, CR Wolfe, C Dun, Y Tang, A Kyrillidis, C Jermaine
Proceedings of the VLDB Endowment, 2022
Mlsys: The new frontier of machine learning systems
A Ratner, D Alistarh, G Alonso, DG Andersen, P Bailis, S Bird, N Carlini, ...
arXiv preprint arXiv:1904.03257, 2019
Demon: Momentum Decay for Improved Neural Network Training
J Chen, C Wolfe, Z Li, A Kyrillidis
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and …, 2020
IHT dies hard: Provable accelerated iterative hard thresholding
R Khanna, A Kyrillidis
Proceedings of the Twenty-First International Conference on Artificial …, 2017
Group-sparse model selection: Hardness and relaxations
L Baldassarre, N Bhan, V Cevher, A Kyrillidis, S Satpathi
IEEE Transactions on Information Theory 62 (11), 6508-6534, 2016
The system can't perform the operation now. Try again later.
Articles 1–20