Tasks across diverse application domains can be posed as large-scale optimization
problems, these include graphics, vision, machine learning, imaging, health, scheduling …

Computational photography systems are becoming increasingly diverse, while
computational resources---for example on mobile platforms---are rapidly increasing. As …

Differentiable optimization algorithms often involve expensive computations of various meta-
gradients. To address this, we design and implement TorchOpt, a new PyTorch-based …

Plug-and-Play (PnP) is a non-convex optimization framework that combines proximal
algorithms, for example, the alternating direction method of multipliers (ADMM), with …

Training of deep learning models depends on gradient descent and end-to-end
differentiation. Under the slogan of differentiable programming, there is an increasing …

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 …

The accelerated proximal point method (APPA), also known as" Catalyst", is a well-
established reduction from convex optimization to approximate proximal point computation …

Learning to optimize (L2O) has gained increasing attention since it demonstrates a
promising path to automating and accelerating the optimization of complicated problems …

Dense conditional random fields (CRF) with Gaussian pairwise potentials have emerged as
a popular framework for several computer vision applications such as stereo …

We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …