Alexander Shekhovtsov
13 papers · 2014–2024 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
ποΈ
Keyword Collector
(61)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Conference Pioneer
Top co-authors
Research topics
Machine Learning
(9)
Deep Learning
(8)
Optimization & Theory Β· Machine Learning
(8)
Mathematics & Optimization
(5)
Artificial Intelligence
(4)
Computer Vision
(4)
Optimization
(4)
Architectures
(3)
Core AI
(3)
Core Methods
(3)
Mathematics
(3)
Models
(3)
Analysis
(2)
Optimization & Theory Β· Deep Learning
(2)
Processing
(2)
Keywords
graphical model
(5)
combinatorial optimization
(3)
map inference
(3)
variance reduction
(2)
gradient estimation
(2)
convolutional neural network
(2)
variational autoencoder
(2)
latent variable model
(2)
label assignment
(2)
evidence lower bound
(2)
straight-through estimator
(2)
differentiable programming
(1)
sampling distribution
(1)
robust estimation
(1)
linear programming
(1)
semi-supervised learning
(1)
exponential family
(1)
parametric optimization
(1)
constraint satisfaction
(1)
energy minimization
(1)
Papers
Symmetric Equilibrium Learning of VAEs
AISTATS 2024
Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator
ICML 2023
Generalized Differentiable RANSAC
ICCV 2023
VAE Approximation Error: ELBO and Exponential Families
ICLR 2022
Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems
CVPR 2020
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
NeurIPS 2020
Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization
AISTATS 2020
Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers
ICLR 2019
MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
ECCV 2018
End-To-End Training of Hybrid CNN-CRF Models for Stereo
CVPR 2017
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
NeurIPS 2016
Maximum Persistency via Iterative Relaxed Inference With Graphical Models
CVPR 2015
Maximum Persistency in Energy Minimization
CVPR 2014