Conference Paper

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling

How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our spatial dependency networks (SDNs), feature maps at each level of a deep neural net are computed in a spatially coherent way, using a sequential gating-based mechanism that distributes contextual information across 2-D space. We show that augmenting the decoder of a hierarchical VAE by spatial dependency...

On maximum-likelihood estimation in the all-or-nothing regime

We study the problem of estimating a rank-1 additive deformation of a Gaussian tensor according to the maximum-likelihood estimator (MLE). The analysis is carried out in the sparse setting, where the underlying signal has a support that scales sublinearly with the total number of dimensions. We show that for Bernoulli distributed signals, the MLE undergoes an all-or-nothing (AoN) phase transition, already established for the minimum mean-square-error estimator (MMSE) in the same problem. The result follows from two main technical points:...

Learning Counterfactual Representations for Estimating Individual Dose-Response Curves

Estimating what would be an individual's potential response to varying levels of exposure to a treatment is of high practical relevance for several important fields, such as healthcare, economics and public policy. However, existing methods for learning to estimate counterfactual outcomes from observational data are either focused on estimating average dose-response curves, or limited to settings with only two treatments that do not have an associated dosage parameter. Here, we present a novel machine-learning approach towards learning counterfactual representations for...

Instance Segmentation for the Quantification of Microplastic Fiber Images

Microplastics pollution has been recognized as a serious environmental concern, with research efforts underway to determine primary causes. Experiments typically generate bright-field images of microplastic fibers that are filtered from water. Environmental decision making in process engineering critically relies on accurate quantification of mi-croplastic fibers in these images. To satisfy the required standards, images are often analyzed manually, resulting in a highly tedious process, with thousands of fiber instances per image. While the shape of individual fibers is relatively simple,...

From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models

DeepHeartBeat: Latent trajectory learning of cardiac cycles using cardiac ultrasounds

Echocardiography monitors the heart movement for noninvasive diagnosis of heart diseases. It proves to be of profound practical importance as it combines low-cost portable instrumentation and rapid image acquisition without the risks of ionizing radiation. However, echocardiograms produce high-dimensional, noisy data which frequently proved difficult to interpret. As a solution, we propose a novel autoencoder-based framework, DeepHeartBeat, to learn human interpretable representations of cardiac cycles from cardiac ultrasound data. Our model encodes high dimensional observations by a cyclic trajectory in...

Unsupervised Mitral Valve Segmentation in Echocardiography with Neural Network Matrix Factorization

Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference

Generative Aging of Brain MR-Images and Prediction of Alzheimer Progression

Generative Aging Of Brain MRI For Early Prediction Of MCI-AD Conversion