986 citations · 2k across the 50 of their papers we have counts for
9 papers · 1 filter
Learning Rate Dropout
Huangxing Lin, Weihong Zeng, Xinghao Ding +3
The performance of a deep neural network is highly dependent on its training, and finding better local optimal solutions is the goal of many optimization algorithms. However, exist…
Risk Bounds for Low Cost Bipartite Ranking
San Gultekin, John Paisley
Bipartite ranking is an important supervised learning problem; however, unlike regression or classification, it has a quadratic dependence on the number of samples. To circumvent t…
Noise2Blur: Online Noise Extraction and Denoising
Huangxing Lin, Weihong Zeng, Xinghao Ding +3
We propose a new framework called Noise2Blur (N2B) for training robust image denoising models without pre-collected paired noisy/clean images. The training of the model requires on…
Accurate Uncertainty Estimation and Decomposition in Ensemble Learning
Jeremiah Zhe Liu, John Paisley, Marianthi-Anna Kioumourtzoglou +1
Ensemble learning is a standard approach to building machine learning systems that capture complex phenomena in real-world data. An important aspect of these systems is the complet…
Reweighted Expectation Maximization
Adji B. Dieng, John Paisley
Training deep generative models with maximum likelihood remains a challenge. The typical workaround is to use variational inference (VI) and maximize a lower bound to the log margi…
Random Function Priors for Correlation Modeling
Aonan Zhang, John Paisley
The likelihood model of high dimensional data can often be expressed as , where is a collection of hidden features shared…
Rain O'er Me: Synthesizing real rain to derain with data distillation
Huangxing Lin, Yanlong Li, Xinghao Ding +3
We present a supervised technique for learning to remove rain from images without using synthetic rain software. The method is based on a two-stage data distillation approach: 1) A…
Spatially Adaptive Ensemble Learning with Calibrated Predictive Uncertainty
Yanran Li, Jeremiah Zhe Liu, John Paisley +2
Air pollution exposure assessment often uses ensembles of spatio-temporal models, but a critical limitation is that conventional methods use deterministic weights and fail to quant…
Global Explanations of Neural Networks: Mapping the Landscape of Predictions
Mark Ibrahim, Melissa Louie, Ceena Modarres +1
A barrier to the wider adoption of neural networks is their lack of interpretability. While local explanation methods exist for one prediction, most global attributions still reduc…