Search Results for author:
Found 22 papers, 11 papers with code
Augmenting Ground-Level PM2.5 Prediction via Kriging-Based Pseudo-Label Generation
We show that the proposed data augmentation strategy helps enhance the performance of the state-of-the-art convolutional neural network-random forest (CNN-RF) model by a reasonable amount, resulting in a noteworthy improvement in spatial correlation and a reduction in prediction error.
Causal Mediation Analysis with Multi-dimensional and Indirectly Observed Mediators
This is important in many scientific applications to identify the underlying mechanisms of a treatment effect.
Domain Adaptation via Rebalanced Sub-domain Alignment
To address this limitation, we propose a novel generalization bound that reweights source classification error by aligning source and target sub-domains.
Estimating Causal Effects using a Multi-task Deep Ensemble
A number of methods have been proposed for causal effect estimation, yet few have demonstrated efficacy in handling data with complex structures, such as images.
Incorporating Prior Knowledge into Neural Networks through an Implicit Composite Kernel
Many deep learning applications could be enhanced by modeling such known properties.
Ranked #1 on
Gaussian Processes
on UCI POWER
Multiple Domain Causal Networks
Finally, we justify our approach by providing theoretical analyses that demonstrate that MDCN improves on the generalization bound of the new, unobserved target center.
AugmentedPCA: A Python Package of Supervised and Adversarial Linear Factor Models
Deep autoencoders are often extended with a supervised or adversarial loss to learn latent representations with desirable properties, such as greater predictivity of labels and outcomes or fairness with respects to a sensitive variable.
Directed Spectrum Measures Improve Latent Network Models Of Neural Populations
We prove that it is compatible with the implicit assumptions of linear factor models, and we provide a method to estimate the DS.
Estimating Potential Outcome Distributions with Collaborating Causal Networks
However, existing methods for estimating treatment effect potential outcome distributions often impose restrictive or simplistic assumptions about these distributions.
Adversarial Factor Models for the Generation of Improved Autism Diagnostic Biomarkers
Second, we show this same model can be used to learn a disentangled representation of multimodal biomarkers that results in an increase in predictive performance.
Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility
We demonstrate the effectiveness of these developments using synthetic data and electrophysiological recordings with an emphasis on how our learned representations can be used to design scientific experiments.
Estimating a Brain Network Predictive of Stress and Genotype with Supervised Autoencoders
Targeted stimulation of the brain has the potential to treat mental illnesses.
Estimating Uncertainty Intervals from Collaborating Networks
We address these challenges by proposing a novel method to capture predictive distributions in regression by defining two neural networks with two distinct loss functions.
Dynamic Embedding on Textual Networks via a Gaussian Process
The relative importance of global versus local structure for the embeddings is learned automatically.
The Secrets of Machine Learning: Ten Things You Wish You Had Known Earlier to be More Effective at Data Analysis
9) There is a method to the madness of deep neural architectures, but not always.
StoryGAN: A Sequential Conditional GAN for Story Visualization
We therefore propose a new story-to-image-sequence generation model, StoryGAN, based on the sequential conditional GAN framework.
Stochastic Bouncy Particle Sampler
We introduce a novel stochastic version of the non-reversible, rejection-free Bouncy Particle Sampler (BPS), a Markov process whose sample trajectories are piecewise linear.
Partition Functions from Rao-Blackwellized Tempered Sampling
Partition functions of probability distributions are important quantities for model evaluation and comparisons.
Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian analogs to popular stochastic optimization methods; however, this connection is not well studied.
Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace and more
Neuroprosthetic decoder training as imitation learning
We describe how training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available.
Deep Temporal Sigmoid Belief Networks for Sequence Modeling
Deep dynamic generative models are developed to learn sequential dependencies in time-series data.
