Mert Pilanci

Cituota

	Visi	Nuo 2020
Šaltiniai	2808	2281
h-rodyklė	26	24
i10-rodyklė	59	55

580

290

145

435

201020112012201320142015201620172018201920202021202220232024202513 2 8 16 12 35 66 97 118 143 283 403 411 565 487 125

Viešas pasiekiamumas

Peržiūrėti viską

50 straipsnių

1 straipsnis

pasiekiami

nepasiekiami

Pagal finansavimo įpareigojimus

Bendraautoriai

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

Stebėti

Mert Pilanci

Stanford University

Patvirtintas el. paštas stanford.edu - Pagrindinis puslapis

Machine Learning Optimization Neural Networks Signal Processing Information Theory


Pavadinimas Rūšiuoti pagal šaltinius Rūšiuoti pagal metus Rūšiuoti pagal pavadinimą	Cituota Cituota	Metai
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	350	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	250	2016
Randomized sketches of convex programs with sharp guarantees M Pilanci, MJ Wainwright IEEE Transactions on Information Theory 61 (9), 5096-5115, 2015	210	2015
Randomized sketches for kernels: Fast and optimal nonparametric regression Y Yang, M Pilanci, MJ Wainwright	205	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	118	2020
Sparse learning via Boolean relaxations M Pilanci, MJ Wainwright, L El Ghaoui Mathematical Programming 151 (1), 63-87, 2015	95	2015
Revealing the structure of deep neural networks via convex duality T Ergen, M Pilanci International Conference on Machine Learning, 3004-3014, 2021	73	2021
Recovery of sparse probability measures via convex programming M Pilanci, L Ghaoui, V Chandrasekaran Advances in Neural Information Processing Systems 25, 2012	64	2012
Convex geometry and duality of over-parameterized neural networks T Ergen, M Pilanci Journal of machine learning research 22 (212), 1-63, 2021	63	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	52	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	45	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	43	2021
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	36	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	36	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
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	35	2021
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	34	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	33	2022
Optimal randomized first-order methods for least-squares problems J Lacotte, M Pilanci International Conference on Machine Learning, 5587-5597, 2020	32	2020
Debiasing distributed second order optimization with surrogate sketching and scaled regularization M Derezinski, B Bartan, M Pilanci, MW Mahoney Advances in Neural Information Processing Systems 33, 6684-6695, 2020	32	2020

Sistema negali atlikti operacijos. Bandykite vėliau dar kartą.

Straipsniai 1–20

Šaltinių per metus

Dubliuoti šaltiniai

Sujungti šaltiniai

Pridėti bendraautoriusBendraautoriai

Stebėti

Cituota

Bendraautoriai