Abstract Machine learning pipelines often rely on optimizers procedures to make discrete
decisions (eg, sorting, picking closest neighbors, or shortest paths). Although these discrete …

The integration of discrete algorithmic components in deep learning architectures has
numerous applications. Recently, Implicit Maximum Likelihood Estimation, a class of …

This paper presents a new approach, called perturb-max, for high-dimensional statistical
inference in graphical models that is based on applying random perturbations followed by …

We consider the structured-output prediction problem through probabilistic approaches and
generalize the" perturb-and-MAP" framework to more challenging weighted Hamming …

Probabilistic graphical models encode hidden dependencies between random variables for
data modelling. Parameter estimation is a crucial part of handling such probabilistic models …

While central to the application of probabilistic models to discrete data, the problem of
marginal inference is in general intractable and efficient approximation schemes need to …

This paper presents a new approach, called perturb-max, for high-dimensional statistical
inference in graphical models that is based on applying random perturbations followed by …

While central to the application of probabilistic models to discrete data, the problem of
marginal inference is in general intractable and efficient approximation schemes need to …