FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2799013664> ?p ?o ?g. }

• W2799013664 abstract "A crucial problem in modern data science is data-driven algorithm design, where the goal is to choose the best algorithm, or algorithm parameters, for a specific application domain. In practice, we often optimize over a parametric algorithm family, searching for parameters with high performance on a collection of typical problem instances. While effective in practice, these procedures generally have not come with provable guarantees. A recent line of work initiated by a seminal paper of Gupta and Roughgarden (2017) analyzes application-specific algorithm selection from a theoretical perspective. We progress this research direction in several important settings. We provide upper and lower bounds on regret for algorithm selection in online settings, where problems arrive sequentially and we must choose parameters online. We also consider differentially private algorithm selection, where the goal is to find good parameters for a set of problems without divulging too much sensitive information contained therein. We analyze several important parameterized families of algorithms, including SDP-rounding schemes for problems formulated as integer quadratic programs as well as greedy techniques for several canonical subset selection problems. The cost function that measures an algorithm's performance is often a volatile piecewise Lipschitz function of its parameters, since a small change to the parameters can lead to a cascade of different decisions made by the algorithm. We present general techniques for optimizing the sum or average of piecewise Lipschitz functions when the underlying functions satisfy a sufficient and general condition called dispersion. Intuitively, a set of piecewise Lipschitz functions is dispersed if no small region contains many of the functions' discontinuities. Using dispersion, we improve over the best-known online learning regret bounds for a variety problems, prove regret bounds for problems not previously studied, and provide matching regret lower bounds. In the private optimization setting, we show how to optimize performance while preserving privacy for several important problems, providing matching upper and lower bounds on performance loss due to privacy preservation. Though algorithm selection is our primary motivation, we believe the notion of dispersion may be of independent interest. Therefore, we present our results for the more general problem of optimizing piecewise Lipschitz functions. Finally, we uncover dispersion in domains beyond algorithm selection, namely, auction design and pricing, providing online and privacy guarantees for these problems as well." @default.
• W2799013664 created "2018-05-07" @default.
• W2799013664 creator A5050640377 @default.
• W2799013664 creator A5068544954 @default.
• W2799013664 creator A5090992760 @default.
• W2799013664 date "2018-10-01" @default.
• W2799013664 modified "2023-09-27" @default.
• W2799013664 title "Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization" @default.
• W2799013664 cites W1570963478 @default.
• W2799013664 cites W1985123706 @default.
• W2799013664 cites W1987141758 @default.
• W2799013664 cites W1992428795 @default.
• W2799013664 cites W2005311763 @default.
• W2799013664 cites W2008690976 @default.
• W2799013664 cites W2026820987 @default.
• W2799013664 cites W2029050771 @default.
• W2799013664 cites W2076618162 @default.
• W2799013664 cites W2087258353 @default.
• W2799013664 cites W2115519224 @default.
• W2799013664 cites W2115905049 @default.
• W2799013664 cites W2123820077 @default.
• W2799013664 cites W2143738202 @default.
• W2799013664 cites W2164143329 @default.
• W2799013664 cites W2167681887 @default.
• W2799013664 cites W2266969817 @default.
• W2799013664 cites W2273828870 @default.
• W2799013664 cites W2282740631 @default.
• W2799013664 cites W2479673198 @default.
• W2799013664 cites W2544285741 @default.
• W2799013664 cites W2559925558 @default.
• W2799013664 cites W2620217443 @default.
• W2799013664 cites W2625599877 @default.
• W2799013664 cites W2796098377 @default.
• W2799013664 cites W2963393294 @default.
• W2799013664 doi "https://doi.org/10.1109/focs.2018.00064" @default.
• W2799013664 hasPublicationYear "2018" @default.
• W2799013664 type Work @default.
• W2799013664 sameAs 2799013664 @default.
• W2799013664 citedByCount "44" @default.
• W2799013664 countsByYear W27990136642018 @default.
• W2799013664 countsByYear W27990136642019 @default.
• W2799013664 countsByYear W27990136642020 @default.
• W2799013664 countsByYear W27990136642021 @default.
• W2799013664 countsByYear W27990136642022 @default.
• W2799013664 countsByYear W27990136642023 @default.
• W2799013664 crossrefType "proceedings-article" @default.
• W2799013664 hasAuthorship W2799013664A5050640377 @default.
• W2799013664 hasAuthorship W2799013664A5068544954 @default.
• W2799013664 hasAuthorship W2799013664A5090992760 @default.
• W2799013664 hasBestOaLocation W27990136642 @default.
• W2799013664 hasConcept C11413529 @default.
• W2799013664 hasConcept C126255220 @default.
• W2799013664 hasConcept C134306372 @default.
• W2799013664 hasConcept C164660894 @default.
• W2799013664 hasConcept C165464430 @default.
• W2799013664 hasConcept C196921405 @default.
• W2799013664 hasConcept C33923547 @default.
• W2799013664 hasConcept C41008148 @default.
• W2799013664 hasConceptScore W2799013664C11413529 @default.
• W2799013664 hasConceptScore W2799013664C126255220 @default.
• W2799013664 hasConceptScore W2799013664C134306372 @default.
• W2799013664 hasConceptScore W2799013664C164660894 @default.
• W2799013664 hasConceptScore W2799013664C165464430 @default.
• W2799013664 hasConceptScore W2799013664C196921405 @default.
• W2799013664 hasConceptScore W2799013664C33923547 @default.
• W2799013664 hasConceptScore W2799013664C41008148 @default.
• W2799013664 hasLocation W27990136641 @default.
• W2799013664 hasLocation W27990136642 @default.
• W2799013664 hasOpenAccess W2799013664 @default.
• W2799013664 hasPrimaryLocation W27990136641 @default.
• W2799013664 hasRelatedWork W1503051695 @default.
• W2799013664 hasRelatedWork W1973679146 @default.
• W2799013664 hasRelatedWork W2072006507 @default.
• W2799013664 hasRelatedWork W2085485627 @default.
• W2799013664 hasRelatedWork W2114040185 @default.
• W2799013664 hasRelatedWork W2357085366 @default.
• W2799013664 hasRelatedWork W2738589326 @default.
• W2799013664 hasRelatedWork W3204175910 @default.
• W2799013664 hasRelatedWork W3205753110 @default.
• W2799013664 hasRelatedWork W4232993046 @default.
• W2799013664 isParatext "false" @default.
• W2799013664 isRetracted "false" @default.
• W2799013664 magId "2799013664" @default.
• W2799013664 workType "article" @default.