Search Results for author:
Found 15 papers, 6 papers with code
Black-Box Variational Inference as a Parametric Approximation to Langevin Dynamics
Variational inference (VI) and Markov chain Monte Carlo (MCMC) are approximate posterior inference algorithms that are often said to have complementary strengths, with VI being fast but biased and MCMC being slower but asymptotically unbiased.
Scalable Spatiotemporal Prediction with Bayesian Neural Fields
Spatiotemporal datasets, which consist of spatially-referenced time series, are ubiquitous in many scientific and business-intelligence applications, such as air pollution monitoring, disease tracking, and cloud-demand forecasting.
Semantic Segmentation with Active Semi-Supervised Representation Learning
We achieve more than 95% of the network's performance on CamVid and CityScapes datasets, utilizing only 12. 1% and 15. 1% of the labeled data, respectively.
Semantic Segmentation with Active Semi-Supervised Learning
Instead, our active learning approach aims to minimize the number of annotations per-image.
Regularized Behavior Value Estimation
Due to bootstrapping, these errors get amplified during training and can lead to divergence, thereby crippling learning.
Addressing Extrapolation Error in Deep Offline Reinforcement Learning
These errors can be compounded by bootstrapping when the function approximator overestimates, leading the value function to *grow unbounded*, thereby crippling learning.
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
Hamiltonian Monte Carlo is a powerful algorithm for sampling from difficult-to-normalize posterior distributions.
Simple, Distributed, and Accelerated Probabilistic Programming
For both a state-of-the-art VAE on 64x64 ImageNet and Image Transformer on 256x256 CelebA-HQ, our approach achieves an optimal linear speedup from 1 to 256 TPUv2 chips.
Aerial Spectral Super-Resolution using Conditional Adversarial Networks
In contrast to the spectra of ground based images, aerial spectral images have low spatial resolution and suffer from higher noise interference.
Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
Deep generative neural networks have proven effective at both conditional and unconditional modeling of complex data distributions.
On the challenges of learning with inference networks on sparse, high-dimensional data
We study parameter estimation in Nonlinear Factor Analysis (NFA) where the generative model is parameterized by a deep neural network.
The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM
We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Markov model (iHMM) that supports a simple, efficient inference scheme.
Learning Activation Functions to Improve Deep Neural Networks
Artificial neural networks typically have a fixed, non-linear activation function at each neuron.
Ranked #168 on
Image Classification
on CIFAR-100
(using extra training data)
Online Learning for Latent Dirichlet Allocation
We develop an online variational Bayes (VB) algorithm for Latent Dirichlet Allocation (LDA).
