Beyond NaN: resiliency of optimization layers in the face of infeasibility
Prior work has successfully incorporated optimization layers as the last layer in neural
networks for various problems, thereby allowing joint learning and planning in one neural …
networks for various problems, thereby allowing joint learning and planning in one neural …
A causal framework for understanding optimisation algorithms
A Causal Framework for Understanding Optimisation Algorithms | SpringerLink Skip to main
content Advertisement SpringerLink Account Menu Find a journal Publish with us Track …
content Advertisement SpringerLink Account Menu Find a journal Publish with us Track …
Evaluating MAP-Elites on constrained optimization problems
S Fioravanzo, G Iacca - arXiv preprint arXiv:1902.00703, 2019 - arxiv.org
Constrained optimization problems are often characterized by multiple constraints that, in
the practice, must be satisfied with different tolerance levels. While some constraints are …
the practice, must be satisfied with different tolerance levels. While some constraints are …
NCVX: A general-purpose optimization solver for constrained machine and deep learning
Imposing explicit constraints are new and increasingly trendy in deep learning, stimulated
by, eg, trustworthy AI that performs robust optimization over complicated perturbation sets …
by, eg, trustworthy AI that performs robust optimization over complicated perturbation sets …
Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
Much as replacing hand-designed features with learned functions has revolutionized how
we solve perceptual tasks, we believe learned algorithms will transform how we train …
we solve perceptual tasks, we believe learned algorithms will transform how we train …
Infeasible deterministic, stochastic, and variance-reduction algorithms for optimization under orthogonality constraints
Orthogonality constraints naturally appear in many machine learning problems, from
Principal Components Analysis to robust neural network training. They are usually solved …
Principal Components Analysis to robust neural network training. They are usually solved …
Improving optimization bounds using machine learning: Decision diagrams meet deep reinforcement learning
Finding tight bounds on the optimal solution is a critical element of practical solution
methods for discrete optimization problems. In the last decade, decision diagrams (DDs) …
methods for discrete optimization problems. In the last decade, decision diagrams (DDs) …
Landscape surrogate: Learning decision losses for mathematical optimization under partial information
Recent works in learning-integrated optimization have shown promise in settings where the
optimization problem is only partially observed or where general-purpose optimizers …
optimization problem is only partially observed or where general-purpose optimizers …
Why is optimization difficult?
This chapter aims to address some of the fundamental issues that are often encountered in
optimization problems, making them difficult to solve. These issues include premature …
optimization problems, making them difficult to solve. These issues include premature …
Training learned optimizers with randomly initialized learned optimizers
Learned optimizers are increasingly effective, with performance exceeding that of hand
designed optimizers such as Adam~\citep {kingma2014adam} on specific tasks\citep …
designed optimizers such as Adam~\citep {kingma2014adam} on specific tasks\citep …