Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912605293> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2912605293 endingPage "4819" @default.
- W2912605293 startingPage "4810" @default.
- W2912605293 abstract "Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical guarantees have been proven for both asymp-totic and finite-time regimes. Algorithmically, LMC-based algorithms resemble the well-known gradient descent (GD) algorithm, where the GD recursion is perturbed by an additive Gaussian noise whose variance has a particular form. Fractional Langevin Monte Carlo (FLMC) is a recently proposed extension of LMC, where the Gaussian noise is replaced by a heavy-tailed α-stable noise. As opposed to its Gaussian counterpart , these heavy-tailed perturbations can incur large jumps and it has been empirically demonstrated that the choice of α-stable noise can provide several advantages in modern machine learning problems, both in optimization and sampling contexts. However, as opposed to LMC, only asymptotic convergence properties of FLMC have been yet established. In this study, we analyze the non-asymptotic behavior of FLMC for non-convex optimization and prove finite-time bounds for its expected suboptimality. Our results show that the weak-error of FLMC increases faster than LMC, which suggests using smaller step-sizes in FLMC. We finally extend our results to the case where the exact gradients are replaced by stochas-tic gradients and show that similar results hold in this setting as well." @default.
- W2912605293 created "2019-02-21" @default.
- W2912605293 creator A5023186133 @default.
- W2912605293 creator A5053326908 @default.
- W2912605293 creator A5055423112 @default.
- W2912605293 date "2019-05-24" @default.
- W2912605293 modified "2023-09-30" @default.
- W2912605293 title "Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization." @default.
- W2912605293 hasPublicationYear "2019" @default.
- W2912605293 type Work @default.
- W2912605293 sameAs 2912605293 @default.
- W2912605293 citedByCount "10" @default.
- W2912605293 countsByYear W29126052932018 @default.
- W2912605293 countsByYear W29126052932019 @default.
- W2912605293 countsByYear W29126052932020 @default.
- W2912605293 countsByYear W29126052932021 @default.
- W2912605293 countsByYear W29126052932023 @default.
- W2912605293 crossrefType "proceedings-article" @default.
- W2912605293 hasAuthorship W2912605293A5023186133 @default.
- W2912605293 hasAuthorship W2912605293A5053326908 @default.
- W2912605293 hasAuthorship W2912605293A5055423112 @default.
- W2912605293 hasConcept C105795698 @default.
- W2912605293 hasConcept C11413529 @default.
- W2912605293 hasConcept C115961682 @default.
- W2912605293 hasConcept C121332964 @default.
- W2912605293 hasConcept C121864883 @default.
- W2912605293 hasConcept C126255220 @default.
- W2912605293 hasConcept C154945302 @default.
- W2912605293 hasConcept C162324750 @default.
- W2912605293 hasConcept C163716315 @default.
- W2912605293 hasConcept C19499675 @default.
- W2912605293 hasConcept C2777303404 @default.
- W2912605293 hasConcept C28826006 @default.
- W2912605293 hasConcept C33923547 @default.
- W2912605293 hasConcept C41008148 @default.
- W2912605293 hasConcept C4199805 @default.
- W2912605293 hasConcept C50522688 @default.
- W2912605293 hasConcept C62520636 @default.
- W2912605293 hasConcept C99498987 @default.
- W2912605293 hasConceptScore W2912605293C105795698 @default.
- W2912605293 hasConceptScore W2912605293C11413529 @default.
- W2912605293 hasConceptScore W2912605293C115961682 @default.
- W2912605293 hasConceptScore W2912605293C121332964 @default.
- W2912605293 hasConceptScore W2912605293C121864883 @default.
- W2912605293 hasConceptScore W2912605293C126255220 @default.
- W2912605293 hasConceptScore W2912605293C154945302 @default.
- W2912605293 hasConceptScore W2912605293C162324750 @default.
- W2912605293 hasConceptScore W2912605293C163716315 @default.
- W2912605293 hasConceptScore W2912605293C19499675 @default.
- W2912605293 hasConceptScore W2912605293C2777303404 @default.
- W2912605293 hasConceptScore W2912605293C28826006 @default.
- W2912605293 hasConceptScore W2912605293C33923547 @default.
- W2912605293 hasConceptScore W2912605293C41008148 @default.
- W2912605293 hasConceptScore W2912605293C4199805 @default.
- W2912605293 hasConceptScore W2912605293C50522688 @default.
- W2912605293 hasConceptScore W2912605293C62520636 @default.
- W2912605293 hasConceptScore W2912605293C99498987 @default.
- W2912605293 hasLocation W29126052931 @default.
- W2912605293 hasOpenAccess W2912605293 @default.
- W2912605293 hasPrimaryLocation W29126052931 @default.
- W2912605293 hasRelatedWork W1964211927 @default.
- W2912605293 hasRelatedWork W2068536004 @default.
- W2912605293 hasRelatedWork W2168326969 @default.
- W2912605293 hasRelatedWork W2328562310 @default.
- W2912605293 hasRelatedWork W2462120248 @default.
- W2912605293 hasRelatedWork W2808623457 @default.
- W2912605293 hasRelatedWork W2885362480 @default.
- W2912605293 hasRelatedWork W2890773834 @default.
- W2912605293 hasRelatedWork W2891787885 @default.
- W2912605293 hasRelatedWork W2903327037 @default.
- W2912605293 hasRelatedWork W2952175606 @default.
- W2912605293 hasRelatedWork W2952789109 @default.
- W2912605293 hasRelatedWork W2953314483 @default.
- W2912605293 hasRelatedWork W2962839956 @default.
- W2912605293 hasRelatedWork W2963481221 @default.
- W2912605293 hasRelatedWork W2963980228 @default.
- W2912605293 hasRelatedWork W3101274747 @default.
- W2912605293 hasRelatedWork W3127100532 @default.
- W2912605293 hasRelatedWork W3174075406 @default.
- W2912605293 hasRelatedWork W3203295954 @default.
- W2912605293 isParatext "false" @default.
- W2912605293 isRetracted "false" @default.
- W2912605293 magId "2912605293" @default.
- W2912605293 workType "article" @default.