How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design

8 August 2019

Papers citing "How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design"

9 / 9 papers shown

Title
Machine Learning for Cutting Planes in Integer Programming: A Survey Arnaud Deza Elias Boutros Khalil 25 24 0 17 Feb 2023
Improved Generalization Bound and Learning of Sparsity Patterns for Data-Driven Low-Rank Approximation Shinsaku Sakaue Taihei Oki 24 3 0 17 Sep 2022
Generalization Bounds for Data-Driven Numerical Linear Algebra Peter L. Bartlett Piotr Indyk Tal Wagner 22 14 0 16 Jun 2022
Formalizing Preferences Over Runtime Distributions Devon R. Graham Kevin Leyton-Brown Tim Roughgarden 16 5 0 25 May 2022
Learning Predictions for Algorithms with Predictions M. Khodak Maria-Florina Balcan Ameet Talwalkar Sergei Vassilvitskii 21 25 0 18 Feb 2022
Differentiable Economics for Randomized Affine Maximizer Auctions Michael J. Curry T. Sandholm John P. Dickerson 41 29 0 06 Feb 2022
A Survey of Methods for Automated Algorithm Configuration Elias Schede Jasmin Brandt Alexander Tornede Marcel Wever Viktor Bengs Eyke Hüllermeier Kevin Tierney 22 48 0 03 Feb 2022
Faster Matchings via Learned Duals M. Dinitz Sungjin Im Thomas Lavastida Benjamin Moseley Sergei Vassilvitskii 17 66 0 20 Jul 2021
Learnable and Instance-Robust Predictions for Online Matching, Flows and Load Balancing Thomas Lavastida Benjamin Moseley R. Ravi Chenyang Xu OOD 34 56 0 23 Nov 2020