Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Anastasios Kyrillidis

Anastasios Kyrillidis

Fast quantum state reconstruction via accelerated non-convex programming


Apr 30, 2021
Junhyung Lyle Kim, George Kollias, Amir Kalev, Ken X. Wei, Anastasios Kyrillidis

Figure 1 for Fast quantum state reconstruction via accelerated non-convex programming
Figure 2 for Fast quantum state reconstruction via accelerated non-convex programming
Figure 3 for Fast quantum state reconstruction via accelerated non-convex programming
Figure 4 for Fast quantum state reconstruction via accelerated non-convex programming
* 46 pages 
  Access Paper or Ask Questions

GIST: Distributed Training for Large-Scale Graph Convolutional Networks


Feb 20, 2021
Cameron R. Wolfe, Jingkang Yang, Arindam Chowdhury, Chen Dun, Artun Bayer, Santiago Segarra, Anastasios Kyrillidis

Figure 1 for GIST: Distributed Training for Large-Scale Graph Convolutional Networks
Figure 2 for GIST: Distributed Training for Large-Scale Graph Convolutional Networks
Figure 3 for GIST: Distributed Training for Large-Scale Graph Convolutional Networks
Figure 4 for GIST: Distributed Training for Large-Scale Graph Convolutional Networks
* 17 pages, 5 figures, pre-print under review 
  Access Paper or Ask Questions

Rank-One Measurements of Low-Rank PSD Matrices Have Small Feasible Sets


Dec 17, 2020
T. Mitchell Roddenberry, Santiago Segarra, Anastasios Kyrillidis

Figure 1 for Rank-One Measurements of Low-Rank PSD Matrices Have Small Feasible Sets
Figure 2 for Rank-One Measurements of Low-Rank PSD Matrices Have Small Feasible Sets
Figure 3 for Rank-One Measurements of Low-Rank PSD Matrices Have Small Feasible Sets
Figure 4 for Rank-One Measurements of Low-Rank PSD Matrices Have Small Feasible Sets
* 22 pages, 3 figures 
  Access Paper or Ask Questions

On Continuous Local BDD-Based Search for Hybrid SAT Solving


Dec 14, 2020
Anastasios Kyrillidis, Moshe Y. Vardi, Zhiwei Zhang

Figure 1 for On Continuous Local BDD-Based Search for Hybrid SAT Solving
Figure 2 for On Continuous Local BDD-Based Search for Hybrid SAT Solving
Figure 3 for On Continuous Local BDD-Based Search for Hybrid SAT Solving
Figure 4 for On Continuous Local BDD-Based Search for Hybrid SAT Solving
* AAAI 21 
  Access Paper or Ask Questions

On Generalization of Adaptive Methods for Over-parameterized Linear Regression


Nov 28, 2020
Vatsal Shah, Soumya Basu, Anastasios Kyrillidis, Sujay Sanghavi

Figure 1 for On Generalization of Adaptive Methods for Over-parameterized Linear Regression
Figure 2 for On Generalization of Adaptive Methods for Over-parameterized Linear Regression
Figure 3 for On Generalization of Adaptive Methods for Over-parameterized Linear Regression
Figure 4 for On Generalization of Adaptive Methods for Over-parameterized Linear Regression
* arXiv admin note: substantial text overlap with arXiv:1811.07055 
  Access Paper or Ask Questions

ImCLR: Implicit Contrastive Learning for Image Classification


Nov 25, 2020
John Chen, Samarth Sinha, Anastasios Kyrillidis

Figure 1 for ImCLR: Implicit Contrastive Learning for Image Classification
Figure 2 for ImCLR: Implicit Contrastive Learning for Image Classification
Figure 3 for ImCLR: Implicit Contrastive Learning for Image Classification
Figure 4 for ImCLR: Implicit Contrastive Learning for Image Classification

  Access Paper or Ask Questions

Bayesian Coresets: An Optimization Perspective


Jul 01, 2020
Jacky Y. Zhang, Rajiv Khanna, Anastasios Kyrillidis, Oluwasanmi Koyejo

Figure 1 for Bayesian Coresets: An Optimization Perspective
Figure 2 for Bayesian Coresets: An Optimization Perspective
Figure 3 for Bayesian Coresets: An Optimization Perspective
Figure 4 for Bayesian Coresets: An Optimization Perspective

  Access Paper or Ask Questions

FourierSAT: A Fourier Expansion-Based Algebraic Framework for Solving Hybrid Boolean Constraints


Dec 02, 2019
Anastasios Kyrillidis, Anshumali Shrivastava, Moshe Y. Vardi, Zhiwei Zhang

Figure 1 for FourierSAT: A Fourier Expansion-Based Algebraic Framework for Solving Hybrid Boolean Constraints
Figure 2 for FourierSAT: A Fourier Expansion-Based Algebraic Framework for Solving Hybrid Boolean Constraints
* The paper was accepted by Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020) 
  Access Paper or Ask Questions

Optimal Mini-Batch Size Selection for Fast Gradient Descent


Nov 15, 2019
Michael P. Perrone, Haidar Khan, Changhoan Kim, Anastasios Kyrillidis, Jerry Quinn, Valentina Salapura

Figure 1 for Optimal Mini-Batch Size Selection for Fast Gradient Descent
Figure 2 for Optimal Mini-Batch Size Selection for Fast Gradient Descent

  Access Paper or Ask Questions

Negative sampling in semi-supervised learning


Nov 12, 2019
John Chen, Vatsal Shah, Anastasios Kyrillidis

Figure 1 for Negative sampling in semi-supervised learning
Figure 2 for Negative sampling in semi-supervised learning
Figure 3 for Negative sampling in semi-supervised learning
Figure 4 for Negative sampling in semi-supervised learning

  Access Paper or Ask Questions

Learning Sparse Distributions using Iterative Hard Thresholding


Nov 07, 2019
Jacky Y. Zhang, Rajiv Khanna, Anastasios Kyrillidis, Oluwasanmi Koyejo

Figure 1 for Learning Sparse Distributions using Iterative Hard Thresholding
Figure 2 for Learning Sparse Distributions using Iterative Hard Thresholding
Figure 3 for Learning Sparse Distributions using Iterative Hard Thresholding
Figure 4 for Learning Sparse Distributions using Iterative Hard Thresholding
* NeurIPS 2019 
  Access Paper or Ask Questions

Decaying momentum helps neural network training


Oct 11, 2019
John Chen, Anastasios Kyrillidis

Figure 1 for Decaying momentum helps neural network training
Figure 2 for Decaying momentum helps neural network training
Figure 3 for Decaying momentum helps neural network training
Figure 4 for Decaying momentum helps neural network training

  Access Paper or Ask Questions

Distributed Learning of Deep Neural Networks using Independent Subnet Training


Oct 04, 2019
Binhang Yuan, Anastasios Kyrillidis, Christopher M. Jermaine

Figure 1 for Distributed Learning of Deep Neural Networks using Independent Subnet Training
Figure 2 for Distributed Learning of Deep Neural Networks using Independent Subnet Training
Figure 3 for Distributed Learning of Deep Neural Networks using Independent Subnet Training
Figure 4 for Distributed Learning of Deep Neural Networks using Independent Subnet Training

  Access Paper or Ask Questions

SysML: The New Frontier of Machine Learning Systems


May 01, 2019
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konečný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Aparna Lakshmiratan, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Murray, Kunle Olukotun, Dimitris Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar


  Access Paper or Ask Questions

Compressing Gradient Optimizers via Count-Sketches


Feb 26, 2019
Ryan Spring, Anastasios Kyrillidis, Vijai Mohan, Anshumali Shrivastava

Figure 1 for Compressing Gradient Optimizers via Count-Sketches
Figure 2 for Compressing Gradient Optimizers via Count-Sketches
Figure 3 for Compressing Gradient Optimizers via Count-Sketches
Figure 4 for Compressing Gradient Optimizers via Count-Sketches
* Initially submitted to WWW 2019 (November 2018) 
  Access Paper or Ask Questions

Minimum norm solutions do not always generalize well for over-parameterized problems


Nov 16, 2018
Vatsal Shah, Anastasios Kyrillidis, Sujay Sanghavi

Figure 1 for Minimum norm solutions do not always generalize well for over-parameterized problems
Figure 2 for Minimum norm solutions do not always generalize well for over-parameterized problems
Figure 3 for Minimum norm solutions do not always generalize well for over-parameterized problems
Figure 4 for Minimum norm solutions do not always generalize well for over-parameterized problems

  Access Paper or Ask Questions

Run Procrustes, Run! On the convergence of accelerated Procrustes Flow


Sep 12, 2018
Anastasios Kyrillidis, Shashanka Ubaru, Georgios Kollias, Kristofer Bouchard

Figure 1 for Run Procrustes, Run! On the convergence of accelerated Procrustes Flow
Figure 2 for Run Procrustes, Run! On the convergence of accelerated Procrustes Flow
Figure 3 for Run Procrustes, Run! On the convergence of accelerated Procrustes Flow
Figure 4 for Run Procrustes, Run! On the convergence of accelerated Procrustes Flow
* 33 pages, footnote 7 removed from previous version, improved constants 
  Access Paper or Ask Questions

Implicit regularization and solution uniqueness in over-parameterized matrix sensing


Jun 06, 2018
Anastasios Kyrillidis, Amir Kalev

Figure 1 for Implicit regularization and solution uniqueness in over-parameterized matrix sensing
Figure 2 for Implicit regularization and solution uniqueness in over-parameterized matrix sensing
* 12 pages 
  Access Paper or Ask Questions

Simple and practical algorithms for $\ell_p$-norm low-rank approximation


May 24, 2018
Anastasios Kyrillidis

Figure 1 for Simple and practical algorithms for $\ell_p$-norm low-rank approximation
Figure 2 for Simple and practical algorithms for $\ell_p$-norm low-rank approximation
Figure 3 for Simple and practical algorithms for $\ell_p$-norm low-rank approximation
Figure 4 for Simple and practical algorithms for $\ell_p$-norm low-rank approximation
* 16 pages, 11 figures, to appear in UAI 2018 
  Access Paper or Ask Questions

Approximate Newton-based statistical inference using only stochastic gradients


May 23, 2018
Tianyang Li, Anastasios Kyrillidis, Liu Liu, Constantine Caramanis

Figure 1 for Approximate Newton-based statistical inference using only stochastic gradients
Figure 2 for Approximate Newton-based statistical inference using only stochastic gradients
Figure 3 for Approximate Newton-based statistical inference using only stochastic gradients
Figure 4 for Approximate Newton-based statistical inference using only stochastic gradients

  Access Paper or Ask Questions

IHT dies hard: Provable accelerated Iterative Hard Thresholding


Dec 26, 2017
Rajiv Khanna, Anastasios Kyrillidis

Figure 1 for IHT dies hard: Provable accelerated Iterative Hard Thresholding
Figure 2 for IHT dies hard: Provable accelerated Iterative Hard Thresholding
Figure 3 for IHT dies hard: Provable accelerated Iterative Hard Thresholding
* 22 pages, accepted to AISTATS 2018 
  Access Paper or Ask Questions

Statistical inference using SGD


Nov 19, 2017
Tianyang Li, Liu Liu, Anastasios Kyrillidis, Constantine Caramanis

Figure 1 for Statistical inference using SGD
Figure 2 for Statistical inference using SGD
Figure 3 for Statistical inference using SGD
Figure 4 for Statistical inference using SGD
* To appear in AAAI 2018 
  Access Paper or Ask Questions

Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions


May 08, 2017
Hemant Tyagi, Anastasios Kyrillidis, Bernd Gärtner, Andreas Krause

Figure 1 for Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions
Figure 2 for Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions
Figure 3 for Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions
Figure 4 for Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions
* To appear in Information and Inference: A Journal of the IMA. Made following changes after review process: (a) Corrected typos throughout the text. (b) Corrected choice of sampling distribution in Section 5, see eqs. (5.2), (5.3). (c) More detailed comparison with existing work in Section 8. (d) Added Section B in appendix on roots of cubic equation 
  Access Paper or Ask Questions

A single-phase, proximal path-following framework


Dec 25, 2016
Quoc Tran-Dinh, Anastasios Kyrillidis, Volkan Cevher

Figure 1 for A single-phase, proximal path-following framework
Figure 2 for A single-phase, proximal path-following framework
Figure 3 for A single-phase, proximal path-following framework
Figure 4 for A single-phase, proximal path-following framework
* 26 pages, 2 figures, 4 tables (This is the first revision. The original one was uploaded on arxiv on March 5, 2016 
  Access Paper or Ask Questions

Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably


Oct 29, 2016
Dohyung Park, Anastasios Kyrillidis, Constantine Caramanis, Sujay Sanghavi

Figure 1 for Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably
Figure 2 for Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably
Figure 3 for Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably
Figure 4 for Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably
* 45 pages 
  Access Paper or Ask Questions

Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems


Oct 01, 2016
Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi

Figure 1 for Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems
Figure 2 for Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems
Figure 3 for Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems
Figure 4 for Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems
* 28 pages 
  Access Paper or Ask Questions