Differentiable Rendering with Reparameterized Volume Sampling

1 code implementation • 21 Feb 2023 • Nikita Morozov, Denis Rakitin, Oleg Desheulin, Dmitry Vetrov, Kirill Struminsky

To generate a pixel of a novel view, it marches a ray through the pixel and computes a weighted sum of radiance emitted from a dense set of ray points.

Novel View Synthesis

Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces

1 code implementation • NeurIPS 2021 • Kirill Struminsky, Artyom Gadetsky, Denis Rakitin, Danil Karpushkin, Dmitry Vetrov

Structured latent variables allow incorporating meaningful prior knowledge into deep learning models.

Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution

1 code implementation • 22 Nov 2019 • Artyom Gadetsky, Kirill Struminsky, Christopher Robinson, Novi Quadrianto, Dmitry Vetrov

Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates.

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates

no code implementations • NeurIPS 2018 • Kirill Struminsky, Simon Lacoste-Julien, Anton Osokin

We study consistency properties of machine learning methods based on minimizing convex surrogates.

General Classification Multi-class Classification

The Deep Weight Prior

2 code implementations • ICLR 2019 • Andrei Atanov, Arsenii Ashukha, Kirill Struminsky, Dmitry Vetrov, Max Welling

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 distribution.

Bayesian Inference Variational Inference

Robust Variational Inference

no code implementations • 28 Nov 2016 • Michael Figurnov, Kirill Struminsky, Dmitry Vetrov

Variational inference is a powerful tool for approximate inference.

Variational Inference