Publication: Beyond Backpropagation: Bilevel Optimization Through Implicit Differentiation and Equilibrium Propagation
Beyond Backpropagation: Bilevel Optimization Through Implicit Differentiation and Equilibrium Propagation
Date
Date
Date
Citations
Zucchet, N., & Sacramento, J. (2022). Beyond Backpropagation: Bilevel Optimization Through Implicit Differentiation and Equilibrium Propagation. Neural Computation, 34, 2309–2346. https://doi.org/10.1162/neco_a_01547
Abstract
Abstract
Abstract
This review examines gradient-based techniques to solve bilevel optimization problems. Bilevel optimization extends the loss minimization framework underlying statistical learning to systems that are implicitly defined through a quantity they minimize. This characterization can be applied to neural networks, optimizers, algorithmic solvers, and even physical systems and allows for greater modeling flexibility compared to the usual explicit definition of such systems. We focus on solving learning problems of this kind through gradient
Metrics
Views
Additional indexing
Creators (Authors)
- Zucchet, Nicolas
- Sacramento, João
Volume
Volume
Volume
Number
Number
Number
Page range/Item number
Page range/Item number
Page range/Item number
Page end
Page end
Page end
Item Type
Item Type
Item Type
In collections
Keywords
Language
Language
Language
Publication date
Publication date
Publication date
Date available
Date available
Date available
ISSN or e-ISSN
ISSN or e-ISSN
ISSN or e-ISSN
OA Status
OA Status
OA Status
Publisher DOI
Metrics
Views
Citations
Zucchet, N., & Sacramento, J. (2022). Beyond Backpropagation: Bilevel Optimization Through Implicit Differentiation and Equilibrium Propagation. Neural Computation, 34, 2309–2346. https://doi.org/10.1162/neco_a_01547