Anastasios Kyrillidis

Bayesian Coresets: An Optimization Perspective

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

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

* 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

Access Paper or Ask Questions

Negative sampling in semi-supervised learning

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

Access Paper or Ask Questions

Learning Sparse Distributions using Iterative Hard Thresholding

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

* NeurIPS 2019

Access Paper or Ask Questions

Decaying momentum helps neural network training

Oct 11, 2019
John Chen, Anastasios Kyrillidis

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

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

* 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

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

* 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

* 12 pages

Access Paper or Ask Questions

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

May 24, 2018
Anastasios Kyrillidis

* 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

Access Paper or Ask Questions

IHT dies hard: Provable accelerated Iterative Hard Thresholding

Dec 26, 2017
Rajiv Khanna, Anastasios Kyrillidis

* 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

* 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

* 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

Anastasios Kyrillidis

Bayesian Coresets: An Optimization Perspective

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

Optimal Mini-Batch Size Selection for Fast Gradient Descent

Negative sampling in semi-supervised learning

Learning Sparse Distributions using Iterative Hard Thresholding

Decaying momentum helps neural network training

Distributed Learning of Deep Neural Networks using Independent Subnet Training

SysML: The New Frontier of Machine Learning Systems

Compressing Gradient Optimizers via Count-Sketches

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

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

Implicit regularization and solution uniqueness in over-parameterized matrix sensing

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

Approximate Newton-based statistical inference using only stochastic gradients

IHT dies hard: Provable accelerated Iterative Hard Thresholding

Statistical inference using SGD

Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions

A single-phase, proximal path-following framework

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

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

Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach

A simple and provable algorithm for sparse diagonal CCA

Learning Sparse Additive Models with Interactions in High Dimensions

Dropping Convexity for Faster Semi-definite Optimization

Convex block-sparse linear regression with expanders -- provably

Trading-off variance and complexity in stochastic gradient descent

Bipartite Correlation Clustering -- Maximizing Agreements