Sökning: onr:"swepub:oai:research.chalmers.se:7959a6a9-d42f-420d-826f-0847af08bca0" >
Recovery Bounds on ...
Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework
-
- Rahbar, Arman, 1992 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Panahi, Ashkan, 1986 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Haghir Chehreghani, Morteza, 1982 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
visa fler...
-
- Dubhashi, Devdatt, 1965 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Krim, Hamid (författare)
- North Carolina State University
-
visa färre...
-
(creator_code:org_t)
- 2023
- 2023
- Engelska.
-
Ingår i: Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022. - 2640-3498. ; 202, s. 28549-28577
- Relaterad länk:
-
https://research.cha...
Abstract
Ämnesord
Stäng
- We develop a novel theoretical framework for understating Optimal Transport (OT) schemes respecting a class structure. For this purpose, we propose a convex OT program with a sum-of-norms regularization term, which provably recovers the underlying class structure under geometric assumptions. Furthermore, we derive an accelerated proximal algorithm with a closed-form projection and proximal operator scheme, thereby affording a more scalable algorithm for computing optimal transport plans. We provide a novel argument for the uniqueness of the optimum even in the absence of strong convexity. Our experiments show that the new regularizer not only results in a better preservation of the class structure in the data but also yields additional robustness to the data geometry, compared to previous regularizers.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas