Mert Pilanci

Cited by

	All	Since 2019
Citations	2668	2285
h-index	26	24
i10-index	55	53

520

260

130

390

20122013201420152016201720182019202020212022202320248 16 12 35 66 99 117 143 283 399 440 505 509

Public access

View all

46 articles

1 article

available

not available

Based on funding mandates

Co-authors

Tolga ErgenResearch Scientist, LG AI ResearchVerified email at stanford.edu
Jonathan LacotteStanford UniversityVerified email at stanford.edu
Martin WainwrightProfessor, EECS/Mathematics, Massachusetts Institute of TechnologyVerified email at mit.edu
Burak BartanResearcher, Qualcomm AI ResearchVerified email at stanford.edu
Arda SahinerStanford UniversityVerified email at stanford.edu
Orhan ArikanBilkent UniversityVerified email at ee.bilkent.edu.tr
John PaulyProfessor of Electrical Engineering, Stanford UniversityVerified email at stanford.edu
Yifei Wang 汪祎非Stanford UniversityVerified email at stanford.edu
Alfred HeroJohn H Holland Distinguished University Professor, University of MichiganVerified email at eecs.umich.edu
Neophytos CharalambidesUniversity of California, San DiegoVerified email at ucsd.edu
Shreyas VasanawalaProfessor of Radiology, Stanford UniversityVerified email at stanford.edu
Yun YangDepartment of Mathematics, University of Maryland, College ParkVerified email at umd.edu
Rajarshi SahaPh.D. candidate, Stanford UniversityVerified email at stanford.edu
Aaron MishkinPhD Student, Stanford UniversityVerified email at cs.stanford.edu
Ibrahim Kurban OzaslanPh.D. Student, USCVerified email at usc.edu
Laurent El GhaouiVinUniversityVerified email at vinuni.edu.vn
Michael MahoneyProfessor of Statistics, UC BerkeleyVerified email at stat.berkeley.edu
Mustafa Çelebi PinarProfessor of Industrial Eng. Bilkent UniversityVerified email at bilkent.edu.tr
Michał DerezińskiAssistant Professor at University of MichiganVerified email at umich.edu
Christopher SandinoResearch Engineer, AppleVerified email at alumni.stanford.edu

Mert Pilanci

Stanford University

Verified email at stanford.edu - Homepage

Machine Learning Optimization Neural Networks Signal Processing Information Theory


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Newton sketch: A near linear-time optimization algorithm with linear-quadratic convergence M Pilanci, MJ Wainwright SIAM Journal on Optimization 27 (1), 205-245, 2017	337	2017
Iterative Hessian sketch: Fast and accurate solution approximation for constrained least-squares M Pilanci, MJ Wainwright Journal of Machine Learning Research 17 (53), 1-38, 2016	248	2016
Randomized sketches of convex programs with sharp guarantees M Pilanci, MJ Wainwright IEEE Transactions on Information Theory 61 (9), 5096-5115, 2015	204	2015
Randomized sketches for kernels: Fast and optimal nonparametric regression Y Yang, M Pilanci, MJ Wainwright	200	2017
Neural networks are convex regularizers: Exact polynomial-time convex optimization formulations for two-layer networks M Pilanci, T Ergen International Conference on Machine Learning, 7695-7705, 2020	113	2020
Sparse learning via Boolean relaxations M Pilanci, MJ Wainwright, L El Ghaoui Mathematical Programming 151 (1), 63-87, 2015	91	2015
Revealing the structure of deep neural networks via convex duality T Ergen, M Pilanci International Conference on Machine Learning, 3004-3014, 2021	77	2021
Recovery of sparse probability measures via convex programming M Pilanci, L Ghaoui, V Chandrasekaran Advances in Neural Information Processing Systems 25, 2012	65	2012
Convex geometry and duality of over-parameterized neural networks T Ergen, M Pilanci Journal of machine learning research 22 (212), 1-63, 2021	62	2021
Implicit convex regularizers of cnn architectures: Convex optimization of two-and three-layer networks in polynomial time T Ergen, M Pilanci arXiv preprint arXiv:2006.14798, 2020	48	2020
Vector-output relu neural network problems are copositive programs: Convex analysis of two layer networks and polynomial-time algorithms A Sahiner, T Ergen, J Pauly, M Pilanci arXiv preprint arXiv:2012.13329, 2020	43	2020
Global optimality beyond two layers: Training deep relu networks via convex programs T Ergen, M Pilanci International Conference on Machine Learning, 2993-3003, 2021	40	2021
Randomized sketches for kernels: Fast and optimal non-parametric regression Y Yang, M Pilanci, MJ Wainwright arXiv preprint arXiv:1501.06195, 2015	36	2015
Newton-LESS: Sparsification without trade-offs for the sketched Newton update M Derezinski, J Lacotte, M Pilanci, MW Mahoney Advances in Neural Information Processing Systems 34, 2835-2847, 2021	34	2021
Demystifying batch normalization in relu networks: Equivalent convex optimization models and implicit regularization T Ergen, A Sahiner, B Ozturkler, J Pauly, M Mardani, M Pilanci arXiv preprint arXiv:2103.01499, 2021	33	2021
The hidden convex optimization landscape of regularized two-layer relu networks: an exact characterization of optimal solutions Y Wang, J Lacotte, M Pilanci International Conference on Learning Representations, 2021	33	2021
Optimal randomized first-order methods for least-squares problems J Lacotte, M Pilanci International Conference on Machine Learning, 5587-5597, 2020	33	2020
Unraveling attention via convex duality: Analysis and interpretations of vision transformers A Sahiner, T Ergen, B Ozturkler, J Pauly, M Mardani, M Pilanci International Conference on Machine Learning, 19050-19088, 2022	32	2022
Convex geometry of two-layer relu networks: Implicit autoencoding and interpretable models T Ergen, M Pilanci International Conference on Artificial Intelligence and Statistics, 4024-4033, 2020	32	2020
Fast convex optimization for two-layer relu networks: Equivalent model classes and cone decompositions A Mishkin, A Sahiner, M Pilanci International Conference on Machine Learning, 15770-15816, 2022	31	2022

The system can't perform the operation now. Try again later.

Articles 1–20

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors