Decision-focused learning: Foundations, state of the art, benchmark and future opportunities

J Mandi, J Kotary, S Berden, M Mulamba… - Journal of Artificial …, 2024 - jair.org
Decision-focused learning (DFL) is an emerging paradigm that integrates machine learning
(ML) and constrained optimization to enhance decision quality by training ML models in an …

A survey of contextual optimization methods for decision-making under uncertainty

U Sadana, A Chenreddy, E Delage, A Forel… - European Journal of …, 2024 - Elsevier
Recently there has been a surge of interest in operations research (OR) and the machine
learning (ML) community in combining prediction algorithms and optimization techniques to …

Raft: Recurrent all-pairs field transforms for optical flow

Z Teed, J Deng - Computer Vision–ECCV 2020: 16th European …, 2020 - Springer
Abstract We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network
architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D …

On neural differential equations

P Kidger - arxiv preprint arxiv:2202.02435, 2022 - arxiv.org
The conjoining of dynamical systems and deep learning has become a topic of great
interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …

Safe control with learned certificates: A survey of neural lyapunov, barrier, and contraction methods for robotics and control

C Dawson, S Gao, C Fan - IEEE Transactions on Robotics, 2023 - ieeexplore.ieee.org
Learning-enabled control systems have demonstrated impressive empirical performance on
challenging control problems in robotics, but this performance comes at the cost of reduced …

Efficient and modular implicit differentiation

M Blondel, Q Berthet, M Cuturi… - Advances in neural …, 2022 - proceedings.neurips.cc
Automatic differentiation (autodiff) has revolutionized machine learning. Itallows to express
complex computations by composing elementary ones in creativeways and removes the …

Theseus: A library for differentiable nonlinear optimization

L Pineda, T Fan, M Monge… - Advances in …, 2022 - proceedings.neurips.cc
We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …

Graph neural networks for scalable radio resource management: Architecture design and theoretical analysis

Y Shen, Y Shi, J Zhang… - IEEE Journal on Selected …, 2020 - ieeexplore.ieee.org
Deep learning has recently emerged as a disruptive technology to solve challenging radio
resource management problems in wireless networks. However, the neural network …

Model-based deep learning: On the intersection of deep learning and optimization

N Shlezinger, YC Eldar, SP Boyd - IEEE Access, 2022 - ieeexplore.ieee.org
Decision making algorithms are used in a multitude of different applications. Conventional
approaches for designing decision algorithms employ principled and simplified modelling …

DC3: A learning method for optimization with hard constraints

PL Donti, D Rolnick, JZ Kolter - arxiv preprint arxiv:2104.12225, 2021 - arxiv.org
Large optimization problems with hard constraints arise in many settings, yet classical
solvers are often prohibitively slow, motivating the use of deep networks as cheap" …