Sökning: onr:"swepub:oai:DiVA.org:umu-223951" >
A Variational Persp...
A Variational Perspective on High-Resolution ODEs
-
- Maskan, Hoomaan (författare)
- Umeå universitet,Institutionen för matematik och matematisk statistik
-
- Zygalakis, Konstantinos C. (författare)
- University of Edinburgh, United Kingdom
-
- Yurtsever, Alp (författare)
- Umeå universitet,Institutionen för matematik och matematisk statistik
-
(creator_code:org_t)
- Neural information processing systems foundation, 2023
- 2023
- Engelska.
-
Ingår i: Advances in Neural Information Processing Systems 36 (NeurIPS 2023). - : Neural information processing systems foundation.
- Relaterad länk:
-
https://papers.nips....
-
visa fler...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- We consider unconstrained minimization of smooth convex functions. We propose a novel variational perspective using forced Euler-Lagrange equation that allows for studying high-resolution ODEs. Through this, we obtain a faster convergence rate for gradient norm minimization using Nesterov's accelerated gradient method. Additionally, we show that Nesterov's method can be interpreted as a rate-matching discretization of an appropriately chosen high-resolution ODE. Finally, using the results from the new variational perspective, we propose a stochastic method for noisy gradients. Several numerical experiments compare and illustrate our stochastic algorithm with state of the art methods.
Ämnesord
- NATURVETENSKAP -- Matematik -- Beräkningsmatematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Computational Mathematics (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)