Search Results for author:
Found 23 papers, 4 papers with code
Symmetric Equilibrium Learning of VAEs
The flexibility and simplicity of this approach allows its application to a wide range of learning scenarios and downstream tasks.
Generalized Differentiable RANSAC
We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.
Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators
Discrete and especially binary random variables occur in many machine learning models, notably in variational autoencoders with binary latent states and in stochastic binary networks.
VAE Approximation Error: ELBO and Exponential Families
The importance of Variational Autoencoders reaches far beyond standalone generative models -- the approach is also used for learning latent representations and can be generalized to semi-supervised learning.
Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks
Training neural networks with binary weights and activations is a challenging problem due to the lack of gradients and difficulty of optimization over discrete weights.
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response.
Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization
We consider the maximum-a-posteriori inference problem in discrete graphical models and study solvers based on the dual block-coordinate ascent rule.
MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications.
Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems
It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models.
Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers
Probabilistic Neural Networks deal with various sources of stochasticity: input noise, dropout, stochastic neurons, parameter uncertainties modeled as random variables, etc.
Stochastic Normalizations as Bayesian Learning
In this work we investigate the reasons why Batch Normalization (BN) improves the generalization performance of deep networks.
Normalization of Neural Networks using Analytic Variance Propagation
We address the problem of estimating statistics of hidden units in a neural network using a method of analytic moment propagation.
Feed-forward Uncertainty Propagation in Belief and Neural Networks
We propose a feed-forward inference method applicable to belief and neural networks.
Generative learning for deep networks
Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional distribution of the outputs given the inputs.
Scalable Full Flow with Learned Binary Descriptors
We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching.
End-to-End Training of Hybrid CNN-CRF Models for Stereo
We propose a novel and principled hybrid CNN+CRF model for stereo estimation.
Complexity of Discrete Energy Minimization Problems
Specifically, we show that general energy minimization, even in the 2-label pairwise case, and planar energy minimization with three or more labels are exp-APX-complete.
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
In particular, the joint M-best diverse labelings can be obtained by running a non-parametric submodular minimization (in the special case - max-flow) solver for M different values of $\gamma$ in parallel, for certain diversity measures.
Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization
Dense image matching is a fundamental low-level problem in Computer Vision, which has received tremendous attention from both discrete and continuous optimization communities.
Maximum Persistency via Iterative Relaxed Inference with Graphical Models
We propose an efficient implementation, which runs in time comparable to a single run of a suboptimal dual solver.
Higher Order Maximum Persistency and Comparison Theorems
For polyhedral relaxations of such problems it is generally not true that variables integer in the relaxed solution will retain the same values in the optimal discrete solution.
Partial Optimality by Pruning for MAP-Inference with General Graphical Models
We propose a novel polynomial time algorithm to obtain a part of its optimal non-relaxed integral solution.
Maximum Persistency in Energy Minimization
We propose a new sufficient condition for partial optimality which is: (1) verifiable in polynomial time (2) invariant to reparametrization of the problem and permutation of labels and (3) includes many existing sufficient conditions as special cases.
