FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135790023> ?p ?o ?g. }

• W3135790023 endingPage "1106" @default.
• W3135790023 startingPage "1033" @default.
• W3135790023 abstract "Abstract Semi-discrete optimal transport problems, which evaluate the Wasserstein distance between a discrete and a generic (possibly non-discrete) probability measure, are believed to be computationally hard. Even though such problems are ubiquitous in statistics, machine learning and computer vision, however, this perception has not yet received a theoretical justification. To fill this gap, we prove that computing the Wasserstein distance between a discrete probability measure supported on two points and the Lebesgue measure on the standard hypercube is already $$#$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mo>#</mml:mo> </mml:math> P-hard. This insight prompts us to seek approximate solutions for semi-discrete optimal transport problems. We thus perturb the underlying transportation cost with an additive disturbance governed by an ambiguous probability distribution, and we introduce a distributionally robust dual optimal transport problem whose objective function is smoothed with the most adverse disturbance distributions from within a given ambiguity set. We further show that smoothing the dual objective function is equivalent to regularizing the primal objective function, and we identify several ambiguity sets that give rise to several known and new regularization schemes. As a byproduct, we discover an intimate relation between semi-discrete optimal transport problems and discrete choice models traditionally studied in psychology and economics. To solve the regularized optimal transport problems efficiently, we use a stochastic gradient descent algorithm with imprecise stochastic gradient oracles. A new convergence analysis reveals that this algorithm improves the best known convergence guarantee for semi-discrete optimal transport problems with entropic regularizers." @default.
• W3135790023 created "2021-03-15" @default.
• W3135790023 creator A5003265461 @default.
• W3135790023 creator A5030361767 @default.
• W3135790023 creator A5065780980 @default.
• W3135790023 date "2022-07-25" @default.
• W3135790023 modified "2023-09-30" @default.
• W3135790023 title "Semi-discrete optimal transport: hardness, regularization and numerical solution" @default.
• W3135790023 cites W1549932963 @default.
• W3135790023 cites W1559169059 @default.
• W3135790023 cites W1568668329 @default.
• W3135790023 cites W1575244755 @default.
• W3135790023 cites W1594039573 @default.
• W3135790023 cites W1632601927 @default.
• W3135790023 cites W1679234839 @default.
• W3135790023 cites W1913007689 @default.
• W3135790023 cites W1978501336 @default.
• W3135790023 cites W1980412153 @default.
• W3135790023 cites W1982143037 @default.
• W3135790023 cites W1985506636 @default.
• W3135790023 cites W1987679122 @default.
• W3135790023 cites W1992208280 @default.
• W3135790023 cites W1994521023 @default.
• W3135790023 cites W1994616650 @default.
• W3135790023 cites W2002603218 @default.
• W3135790023 cites W2004548680 @default.
• W3135790023 cites W2005270074 @default.
• W3135790023 cites W2006957355 @default.
• W3135790023 cites W2009172320 @default.
• W3135790023 cites W2022829242 @default.
• W3135790023 cites W2024484010 @default.
• W3135790023 cites W2028852533 @default.
• W3135790023 cites W2031485386 @default.
• W3135790023 cites W2033442452 @default.
• W3135790023 cites W2036996178 @default.
• W3135790023 cites W2046267801 @default.
• W3135790023 cites W2049106345 @default.
• W3135790023 cites W2049153601 @default.
• W3135790023 cites W2052643735 @default.
• W3135790023 cites W2057869046 @default.
• W3135790023 cites W2069737635 @default.
• W3135790023 cites W2082789409 @default.
• W3135790023 cites W2083259237 @default.
• W3135790023 cites W2084990336 @default.
• W3135790023 cites W2086161653 @default.
• W3135790023 cites W2087583752 @default.
• W3135790023 cites W2093222011 @default.
• W3135790023 cites W2093417350 @default.
• W3135790023 cites W2117371776 @default.
• W3135790023 cites W2120991802 @default.
• W3135790023 cites W2121210949 @default.
• W3135790023 cites W2125993116 @default.
• W3135790023 cites W2125999230 @default.
• W3135790023 cites W2132442278 @default.
• W3135790023 cites W2132883347 @default.
• W3135790023 cites W2143668817 @default.
• W3135790023 cites W2146245948 @default.
• W3135790023 cites W2156521909 @default.
• W3135790023 cites W2161086299 @default.
• W3135790023 cites W2164260102 @default.
• W3135790023 cites W2188662124 @default.
• W3135790023 cites W2211336473 @default.
• W3135790023 cites W2222512263 @default.
• W3135790023 cites W2312355711 @default.
• W3135790023 cites W2395721444 @default.
• W3135790023 cites W2509351257 @default.
• W3135790023 cites W2525755238 @default.
• W3135790023 cites W2528351259 @default.
• W3135790023 cites W2539033431 @default.
• W3135790023 cites W2543484873 @default.
• W3135790023 cites W2579406944 @default.
• W3135790023 cites W2603538444 @default.
• W3135790023 cites W2616032077 @default.
• W3135790023 cites W2626618681 @default.
• W3135790023 cites W2724892359 @default.
• W3135790023 cites W2735418187 @default.
• W3135790023 cites W2759497469 @default.
• W3135790023 cites W2766966154 @default.
• W3135790023 cites W2774644863 @default.
• W3135790023 cites W2795320988 @default.
• W3135790023 cites W2803781351 @default.
• W3135790023 cites W2962792820 @default.
• W3135790023 cites W2963048020 @default.
• W3135790023 cites W2963403405 @default.
• W3135790023 cites W2963450292 @default.
• W3135790023 cites W2963527517 @default.
• W3135790023 cites W2963981973 @default.
• W3135790023 cites W2964218480 @default.
• W3135790023 cites W3005524234 @default.
• W3135790023 cites W3013479538 @default.
• W3135790023 cites W3016365586 @default.
• W3135790023 cites W3044707062 @default.
• W3135790023 cites W3103657382 @default.
• W3135790023 cites W3105981035 @default.
• W3135790023 cites W3106032721 @default.
• W3135790023 cites W3124891448 @default.
• W3135790023 cites W3125192983 @default.
• W3135790023 cites W3131762332 @default.

• next