FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033972871> ?p ?o ?g. }

• W3033972871 abstract "We propose neural control variates (NCV) for unbiased variance reduction in parametric Monte Carlo integration. So far, the core challenge of applying the method of control variates has been finding a good approximation of the integrand that is cheap to integrate. We show that a set of neural networks can face that challenge: a normalizing flow that approximates the shape of the integrand and another neural network that infers the solution of the integral equation. We also propose to leverage a neural importance sampler to estimate the difference between the original integrand and the learned control variate. To optimize the resulting parametric estimator, we derive a theoretically optimal, variance-minimizing loss function, and propose an alternative, composite loss for stable online training in practice. When applied to light transport simulation, neural control variates are capable of matching the state-of-the-art performance of other unbiased approaches, while providing means to develop more performant, practical solutions. Specifically, we show that the learned light-field approximation is of sufficient quality for high-order bounces, allowing us to omit the error correction and thereby dramatically reduce the noise at the cost of negligible visible bias." @default.
• W3033972871 created "2020-06-12" @default.
• W3033972871 creator A5027562963 @default.
• W3033972871 creator A5037043205 @default.
• W3033972871 creator A5050969104 @default.
• W3033972871 creator A5090337152 @default.
• W3033972871 date "2020-06-02" @default.
• W3033972871 modified "2023-09-23" @default.
• W3033972871 title "Neural Control Variates" @default.
• W3033972871 cites W1499749778 @default.
• W3033972871 cites W1522301498 @default.
• W3033972871 cites W1523910963 @default.
• W3033972871 cites W1533861849 @default.
• W3033972871 cites W155909673 @default.
• W3033972871 cites W1564611446 @default.
• W3033972871 cites W1583912456 @default.
• W3033972871 cites W1866230956 @default.
• W3033972871 cites W1873595945 @default.
• W3033972871 cites W1905963256 @default.
• W3033972871 cites W1972029927 @default.
• W3033972871 cites W2002337266 @default.
• W3033972871 cites W2004973016 @default.
• W3033972871 cites W2006722592 @default.
• W3033972871 cites W2014945091 @default.
• W3033972871 cites W2036766781 @default.
• W3033972871 cites W2061724927 @default.
• W3033972871 cites W206338015 @default.
• W3033972871 cites W2070792261 @default.
• W3033972871 cites W2076128027 @default.
• W3033972871 cites W2084292686 @default.
• W3033972871 cites W2086913350 @default.
• W3033972871 cites W2090346540 @default.
• W3033972871 cites W2090950744 @default.
• W3033972871 cites W2091019609 @default.
• W3033972871 cites W2104067967 @default.
• W3033972871 cites W2117358914 @default.
• W3033972871 cites W2127052460 @default.
• W3033972871 cites W2134036633 @default.
• W3033972871 cites W2135596692 @default.
• W3033972871 cites W2139189324 @default.
• W3033972871 cites W2142380402 @default.
• W3033972871 cites W2150665263 @default.
• W3033972871 cites W2151047098 @default.
• W3033972871 cites W2151084831 @default.
• W3033972871 cites W2167779323 @default.
• W3033972871 cites W2194775991 @default.
• W3033972871 cites W2409550820 @default.
• W3033972871 cites W2470326759 @default.
• W3033972871 cites W2553326439 @default.
• W3033972871 cites W2584295865 @default.
• W3033972871 cites W2587284713 @default.
• W3033972871 cites W2755063399 @default.
• W3033972871 cites W2806367298 @default.
• W3033972871 cites W2808746463 @default.
• W3033972871 cites W2940630699 @default.
• W3033972871 cites W2942074357 @default.
• W3033972871 cites W2949117887 @default.
• W3033972871 cites W2952669938 @default.
• W3033972871 cites W2953952939 @default.
• W3033972871 cites W2956353133 @default.
• W3033972871 cites W2958246682 @default.
• W3033972871 cites W2963090522 @default.
• W3033972871 cites W2963851840 @default.
• W3033972871 cites W2964239127 @default.
• W3033972871 cites W2964343746 @default.
• W3033972871 cites W2966144556 @default.
• W3033972871 cites W2968257580 @default.
• W3033972871 cites W2983579636 @default.
• W3033972871 cites W2992005611 @default.
• W3033972871 cites W2992035660 @default.
• W3033972871 cites W3043139608 @default.
• W3033972871 cites W72061137 @default.
• W3033972871 hasPublicationYear "2020" @default.
• W3033972871 type Work @default.
• W3033972871 sameAs 3033972871 @default.
• W3033972871 citedByCount "1" @default.
• W3033972871 countsByYear W30339728712021 @default.
• W3033972871 crossrefType "posted-content" @default.
• W3033972871 hasAuthorship W3033972871A5027562963 @default.
• W3033972871 hasAuthorship W3033972871A5037043205 @default.
• W3033972871 hasAuthorship W3033972871A5050969104 @default.
• W3033972871 hasAuthorship W3033972871A5090337152 @default.
• W3033972871 hasConcept C105795698 @default.
• W3033972871 hasConcept C111350023 @default.
• W3033972871 hasConcept C11413529 @default.
• W3033972871 hasConcept C117251300 @default.
• W3033972871 hasConcept C121683094 @default.
• W3033972871 hasConcept C121955636 @default.
• W3033972871 hasConcept C126255220 @default.
• W3033972871 hasConcept C13153151 @default.
• W3033972871 hasConcept C144133560 @default.
• W3033972871 hasConcept C153083717 @default.
• W3033972871 hasConcept C154945302 @default.
• W3033972871 hasConcept C185429906 @default.
• W3033972871 hasConcept C19499675 @default.
• W3033972871 hasConcept C196083921 @default.
• W3033972871 hasConcept C28826006 @default.
• W3033972871 hasConcept C33923547 @default.
• W3033972871 hasConcept C41008148 @default.
• W3033972871 hasConcept C50644808 @default.

• next