4 papers
Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces
Kirill Struminsky, Artyom Gadetsky, Denis Rakitin +2
Structured latent variables allow incorporating meaningful prior knowledge into deep learning models. However, learning with such variables remains challenging because of their dis…
Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution
Artyom Gadetsky, Kirill Struminsky, Christopher Robinson +2
Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates. Modern variance reduction techn…
Quantifying Learning Guarantees for Convex but Inconsistent Surrogates
Kirill Struminsky, Simon Lacoste-Julien, Anton Osokin
We study consistency properties of machine learning methods based on minimizing convex surrogates. We extend the recent framework of Osokin et al. (2017) for the quantitative analy…
The Deep Weight Prior
Andrei Atanov, Arsenii Ashukha, Kirill Struminsky +2
Bayesian inference is known to provide a general framework for incorporating prior knowledge or specific properties into machine learning models via carefully choosing a prior dist…