Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900900389> ?p ?o ?g. }
- W2900900389 abstract "Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these two kinds of methodology, and limited understanding of relative strengths and weaknesses. Moreover, existing results have been obtained primarily in the setting of convex functions (for optimization) and log-concave functions (for sampling). In this setting, where local properties determine global properties, optimization algorithms are unsurprisingly more efficient computationally than sampling algorithms. We instead examine a class of nonconvex objective functions that arise in mixture modeling and multi-stable systems. In this nonconvex setting, we find that the computational complexity of sampling algorithms scales linearly with the model dimension while that of optimization algorithms scales exponentially." @default.
- W2900900389 created "2018-11-29" @default.
- W2900900389 creator A5041806431 @default.
- W2900900389 creator A5049812527 @default.
- W2900900389 creator A5061093552 @default.
- W2900900389 creator A5073741652 @default.
- W2900900389 creator A5082311500 @default.
- W2900900389 date "2018-11-20" @default.
- W2900900389 modified "2023-09-28" @default.
- W2900900389 title "Sampling Can Be Faster Than Optimization" @default.
- W2900900389 cites W1518824415 @default.
- W2900900389 cites W1556278552 @default.
- W2900900389 cites W1579271636 @default.
- W2900900389 cites W1953619313 @default.
- W2900900389 cites W1973744698 @default.
- W2900900389 cites W1974932891 @default.
- W2900900389 cites W1980018091 @default.
- W2900900389 cites W1981326159 @default.
- W2900900389 cites W1998060273 @default.
- W2900900389 cites W2008703230 @default.
- W2900900389 cites W2022004112 @default.
- W2900900389 cites W2024060531 @default.
- W2900900389 cites W2024476015 @default.
- W2900900389 cites W2047289743 @default.
- W2900900389 cites W2057291289 @default.
- W2900900389 cites W2082856185 @default.
- W2900900389 cites W2085266415 @default.
- W2900900389 cites W2099111195 @default.
- W2900900389 cites W2101517901 @default.
- W2900900389 cites W2130401121 @default.
- W2900900389 cites W2138855972 @default.
- W2900900389 cites W2141436719 @default.
- W2900900389 cites W2141649633 @default.
- W2900900389 cites W2146764432 @default.
- W2900900389 cites W2154409654 @default.
- W2900900389 cites W2159000620 @default.
- W2900900389 cites W2222154095 @default.
- W2900900389 cites W2323824333 @default.
- W2900900389 cites W2346336558 @default.
- W2900900389 cites W24149473 @default.
- W2900900389 cites W2427484745 @default.
- W2900900389 cites W2562674776 @default.
- W2900900389 cites W2734023839 @default.
- W2900900389 cites W2746461338 @default.
- W2900900389 cites W2762725970 @default.
- W2900900389 cites W2766533971 @default.
- W2900900389 cites W2783417494 @default.
- W2900900389 cites W2788191306 @default.
- W2900900389 cites W2788368350 @default.
- W2900900389 cites W2802698595 @default.
- W2900900389 cites W2883697110 @default.
- W2900900389 cites W2888664689 @default.
- W2900900389 cites W2911398476 @default.
- W2900900389 cites W2952969080 @default.
- W2900900389 cites W2955467429 @default.
- W2900900389 cites W2962794482 @default.
- W2900900389 cites W2962839956 @default.
- W2900900389 cites W2963164444 @default.
- W2900900389 cites W2963326510 @default.
- W2900900389 cites W2964301034 @default.
- W2900900389 cites W2977850992 @default.
- W2900900389 cites W3102502737 @default.
- W2900900389 cites W3123239371 @default.
- W2900900389 cites W3124367822 @default.
- W2900900389 cites W3141595720 @default.
- W2900900389 cites W385466589 @default.
- W2900900389 cites W88155604 @default.
- W2900900389 hasPublicationYear "2018" @default.
- W2900900389 type Work @default.
- W2900900389 sameAs 2900900389 @default.
- W2900900389 citedByCount "7" @default.
- W2900900389 countsByYear W29009003892019 @default.
- W2900900389 countsByYear W29009003892020 @default.
- W2900900389 crossrefType "posted-content" @default.
- W2900900389 hasAuthorship W2900900389A5041806431 @default.
- W2900900389 hasAuthorship W2900900389A5049812527 @default.
- W2900900389 hasAuthorship W2900900389A5061093552 @default.
- W2900900389 hasAuthorship W2900900389A5073741652 @default.
- W2900900389 hasAuthorship W2900900389A5082311500 @default.
- W2900900389 hasConcept C105795698 @default.
- W2900900389 hasConcept C106131492 @default.
- W2900900389 hasConcept C111472728 @default.
- W2900900389 hasConcept C11413529 @default.
- W2900900389 hasConcept C126255220 @default.
- W2900900389 hasConcept C137836250 @default.
- W2900900389 hasConcept C138885662 @default.
- W2900900389 hasConcept C140779682 @default.
- W2900900389 hasConcept C19499675 @default.
- W2900900389 hasConcept C202444582 @default.
- W2900900389 hasConcept C31972630 @default.
- W2900900389 hasConcept C33676613 @default.
- W2900900389 hasConcept C33923547 @default.
- W2900900389 hasConcept C41008148 @default.
- W2900900389 hasConcept C52740198 @default.
- W2900900389 hasConcept C63882131 @default.
- W2900900389 hasConceptScore W2900900389C105795698 @default.
- W2900900389 hasConceptScore W2900900389C106131492 @default.
- W2900900389 hasConceptScore W2900900389C111472728 @default.
- W2900900389 hasConceptScore W2900900389C11413529 @default.
- W2900900389 hasConceptScore W2900900389C126255220 @default.