∇-prox: Differentiable proximal algorithm modeling for large-scale optimization
Tasks across diverse application domains can be posed as large-scale optimization
problems, these include graphics, vision, machine learning, imaging, health, scheduling …
problems, these include graphics, vision, machine learning, imaging, health, scheduling …
Proximal: Efficient image optimization using proximal algorithms
Computational photography systems are becoming increasingly diverse, while
computational resources---for example on mobile platforms---are rapidly increasing. As …
computational resources---for example on mobile platforms---are rapidly increasing. As …
Torchopt: An efficient library for differentiable optimization
Differentiable optimization algorithms often involve expensive computations of various meta-
gradients. To address this, we design and implement TorchOpt, a new PyTorch-based …
gradients. To address this, we design and implement TorchOpt, a new PyTorch-based …
Tfpnp: Tuning-free plug-and-play proximal algorithms with applications to inverse imaging problems
Plug-and-Play (PnP) is a non-convex optimization framework that combines proximal
algorithms, for example, the alternating direction method of multipliers (ADMM), with …
algorithms, for example, the alternating direction method of multipliers (ADMM), with …
Backpropagation with callbacks: Foundations for efficient and expressive differentiable programming
Training of deep learning models depends on gradient descent and end-to-end
differentiation. Under the slogan of differentiable programming, there is an increasing …
differentiation. Under the slogan of differentiable programming, there is an increasing …
iPiano: Inertial proximal algorithm for nonconvex optimization
In this paper we study an algorithm for solving a minimization problem composed of a
differentiable (possibly nonconvex) and a convex (possibly nondifferentiable) function. The …
differentiable (possibly nonconvex) and a convex (possibly nondifferentiable) function. The …
Recapp: Crafting a more efficient catalyst for convex optimization
The accelerated proximal point method (APPA), also known as" Catalyst", is a well-
established reduction from convex optimization to approximate proximal point computation …
established reduction from convex optimization to approximate proximal point computation …
Scalable learning to optimize: A learned optimizer can train big models
Learning to optimize (L2O) has gained increasing attention since it demonstrates a
promising path to automating and accelerating the optimization of complicated problems …
promising path to automating and accelerating the optimization of complicated problems …
Efficient continuous relaxations for dense CRF
Dense conditional random fields (CRF) with Gaussian pairwise potentials have emerged as
a popular framework for several computer vision applications such as stereo …
a popular framework for several computer vision applications such as stereo …
Theseus: A library for differentiable nonlinear optimization
We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …