Filters








3,309 Hits in 3.1 sec

Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems [article]

Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, Colin White
2018 arXiv   pre-print
In this way, our work both contributes to the foundations of algorithm configuration and pushes the boundaries of learning theory, since the algorithm classes we analyze consist of multi-stage optimization  ...  We address this problem for clustering, max-cut, and other partitioning problems, such as integer quadratic programming, by designing computationally efficient and sample efficient learning algorithms  ...  We approach application-specific algorithm configuration via a learning-theoretic framework wherein an application domain is modeled as a distribution over problem instances.  ... 
arXiv:1611.04535v4 fatcat:tj5j3iyinvd6ffkbwyy3e6didm

Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees

Maria-Florina Balcan, Tuomas Sandholm, Ellen Vitercik
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Our algorithm can help compile a configuration portfolio, or it can be used to select the input to a configuration algorithm for finite parameter spaces.  ...  We provide an algorithm that learns a finite set of promising parameters from within an infinite set.  ...  CCF-1733556, the ARO under award W911NF-17-1-0082, an Amazon Research Award, an AWS Machine Learning Research Award, and a Bloomberg Data Science research grant.  ... 
doi:10.1609/aaai.v34i04.5721 fatcat:4kliqd5hy5dtvmlidfyoeimc5i

Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees [article]

Maria-Florina Balcan, Tuomas Sandholm, Ellen Vitercik
2020 arXiv   pre-print
Our algorithm can help compile a configuration portfolio, or it can be used to select the input to a configuration algorithm for finite parameter spaces.  ...  We provide an algorithm that learns a finite set of promising parameters from within an infinite set.  ...  In this work, we develop the foundations of automated algorithm configuration via machine learning.  ... 
arXiv:1905.10819v3 fatcat:okbr5tep6nchrhav7nx57eiobm

Tropical Tensor Network for Ground States of Spin Glasses [article]

Jin-Guo Liu, Lei Wang, Pan Zhang
2021 arXiv   pre-print
Our approach provides baselines and benchmarks for exact algorithms for spin glasses and combinatorial optimization problems, and for evaluating heuristic algorithms and mean-field theories.  ...  We present a unified exact tensor network approach to compute the ground state energy, identify the optimal configuration, and count the number of solutions for spin glasses.  ...  Introduction-Combinatorial optimization problems have fundamental theoretical interests in statistical physics and computer science.  ... 
arXiv:2008.06888v2 fatcat:jtdiyori7bewfkxsex63ywdhyq

Backbone Analysis and Applications in Heuristic Algorithm Design

He JIANG, Tie QIU, Yan HU, Ming-Chu LI, Zhong-Xuan LUO
2011 ACTA AUTOMATICA SINICA  
A morphing procedure to supplement a simulated annealing heuristic for cost-and coverage-correlated set-covering problems. Annals of Operations Research, 1999, 86(1): 611−627 45 Boese K D.  ...  The existing research of backbone consists of three areas, including the basic theoretical research focusing on investigation of the relationship between the backbone and computational complexity, the  ...  Searching for backbones -a high-performance parallel algorithm for solving combinatorial optimization problems.  ... 
doi:10.3724/sp.j.1004.2011.00257 fatcat:dbvrdmoqynaulcpwrfiruateq4

Optimal Segmentation of Directed Graph and the Minimum Number of Feedback Arcs

Yi-Zhi Xu, Hai-Jun Zhou
2017 Journal of statistical physics  
The minimum feedback arc density of a given random digraph ensemble is then obtained by extrapolating the theoretical results to the limit of large D.  ...  We solve the D-segmentation problem by the replica-symmetric mean field theory and belief-propagation heuristic algorithms.  ...  One of the authors (HJZ) acknowledges the hospitality of the Asia Pacific Center for Theoretical Physics (APCTP, Pohang, Korea) where the theoretical part of this project was carried out during a short  ... 
doi:10.1007/s10955-017-1860-5 fatcat:4ybx4jvs3zfnrg5cysvgjdmrtq

Bayesian statistical learning for big data biology

Christopher Yau, Kieran Campbell
2019 Biophysical Reviews  
We then describe the use of Bayesian learning in single-cell biology for the analysis of high-dimensional, large data sets.  ...  This review describes the theoretical foundations underlying Bayesian statistics and outlines the computational frameworks for implementing Bayesian inference in practice.  ...  Direct computation is typically intractable, due to the curse of dimensionality for any problem of even moderate dimensionality, which results in a combinatorial explosion in the number of configurations  ... 
doi:10.1007/s12551-019-00499-1 pmid:30729409 pmcid:PMC6381359 fatcat:26l5tkuawrarbni4vc6srasvd4

Privacy Preserving Linear Programming [article]

Yuan Hong, Jaideep Vaidya, Nicholas Rizzo, Qi Liu
2016 arXiv   pre-print
In summary, we propose a set of efficient and secure transformation based techniques that create significant value-added benefits of being independent of the specific algorithms used for solving the linear  ...  Finally, we extend the technique for securely solving two-party arbitrarily partitioned linear programming problems to a multi-party scenario.  ...  Acknowledgments This work is partially supported by the National Science Foundation under Grants No. CNS-0746943 and CNS-1618221.  ... 
arXiv:1610.02339v1 fatcat:spgrdyeeyreyxh5ik6o5bkaafa

Toward IoT-Friendly Learning Models

Ernesto Damiani, Gabriele Gianini, Michelangelo Ceci, Donato Malerba
2018 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)  
We argue that knowledge of the composite nature of the learning process, as well as of the adversarial character of the relationship among phases, can help in developing heuristics for improving the learning  ...  We demonstrate the application of this principle, by a multiple kernel learning approach, based on the exploration of the partition lattice driven by the natural partitioning of the feature set.  ...  Choosing a kernel is itself a problem; one can explore the combinatorial space of dimensions and assess results by crossvalidation.  ... 
doi:10.1109/icdcs.2018.00128 dblp:conf/icdcs/DamianiGCM18 fatcat:3vym7eppizfc3m4ibephvclafy

From Relational Data to Graphs: Inferring Significant Links Using Generalized Hypergeometric Ensembles [chapter]

Giona Casiraghi, Vahan Nanumyan, Ingo Scholtes, Frank Schweitzer
2017 Lecture Notes in Computer Science  
The inference of network topologies from relational data is an important problem in data analysis.  ...  Exemplary applications include the reconstruction of social ties from data on human interactions, the inference of gene co-expression networks from DNA microarray data, or the learning of semantic relationships  ...  We thus argue that our work advances the theoretical foundation for the mining of relational data on social systems.  ... 
doi:10.1007/978-3-319-67256-4_11 fatcat:tdxkugui2zgkfjjgxvdo5athni

Quantum annealing: next-generation computation and how to implement it when information is missing

Masayuki Ohzeki, Chako Takahashi, Shuntaro Okada, Masayoshi Terabe, Shinichiro Taguchi, Kazuyuki Tanaka
2018 Nonlinear Theory and Its Applications IEICE  
Recently, several powerful machines dedicated to solving combinatorial optimization problems through the Ising-model formulation have appeared.  ...  Furthermore, we analyze the theoretical limitations of our proposed method by employing the replica method, which is a sophisticated tool in statistical mechanics.  ...  Acknowledgments One of the authors (M. O.) was partially supported by Inamori Foundation, KAKENHI Nos. 15H03699, 16H04832, and 16K13849, and JST-START. One of the authors (C.  ... 
doi:10.1587/nolta.9.392 fatcat:5aps5timqne4vn6xejns5cry6y

Local Graph Partitions for Approximation and Testing

Avinatan Hassidim, Jonathan A. Kelner, Huy N. Nguyen, Krzysztof Onak
2009 2009 50th Annual IEEE Symposium on Foundations of Computer Science  
We introduce a new tool for approximation and testing algorithms called partitioning oracles.  ...  For instance: • We give constant-time approximation algorithms for the size of the minimum vertex cover, the minimum dominating set, and the maximum independent set for any class of graphs with an excluded  ...  Avinatan and Krzysztof thank Erik Demain for an inspiring early discussion. Avinatan thanks Noga Alon for inspiring discussions. Krzysztof thanks Fabian Kuhn for pointing out [13] .  ... 
doi:10.1109/focs.2009.77 dblp:conf/focs/HassidimKNO09 fatcat:reo7i3vue5djfglqkexjmdk42m

Data-driven Algorithm Design [article]

Maria-Florina Balcan
2020 arXiv   pre-print
The challenge is that for many combinatorial problems of significant importance including partitioning, subset selection, and alignment problems, a small tweak to the parameters can cause a cascade of  ...  In this chapter, we survey recent work that helps put data-driven combinatorial algorithm design on firm foundations.  ...  of random problem parameters in algorithm configuration instances.  ... 
arXiv:2011.07177v1 fatcat:xozyiox2pjgtxftntoxoosumt4

Abstract Combinatorial Programs and Efficient Property Testers

Artur Czumaj, Christian Sohler
2005 SIAM journal on computing (Print)  
Among others, we present efficient property testing algorithms for geometric clustering problems, for the reversal distance problem, for graph and hypergraph coloring problems.  ...  We apply our framework to a variety of classical combinatorial problems.  ...  graph partitioning problems.  ... 
doi:10.1137/s009753970444199x fatcat:vqohwu2vcvealhnej6gfeh7zqq

Thermodynamic-RAM technology stack

M. Alexander Nugent, Timothy W. Molter
2017 International Journal of Parallel, Emergent and Distributed Systems  
Bringing us closer to brain-like neural computation, kT-RAM will provide a general-purpose adaptive hardware resource to existing computing platforms enabling fast and low-power machine learning capabilities  ...  of AHaH Computing and integrate it into today's digital computing systems.  ...  Campbell from Boise State University for graciously providing us with memristor device data.  ... 
doi:10.1080/17445760.2017.1314472 fatcat:e2mm7stwzzhldklms72vywmd6a
« Previous Showing results 1 — 15 out of 3,309 results