Author name cluster

Debasish Das

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

ECAI Conference 2012 Conference Paper

Mining Extremes: Severe Rainfall and Climate Change

Debasish Das
Evan Kodra
Zoran Obradovic
Auroop R. Ganguly

Theoretical developments for the analysis and modeling of extreme value data have tended to focus on limiting cases and assumptions of independence. However, massive datasets from models and sensors, space-time dimensionality, comp dependence structures, long-memory, long-range and low frequency processes all motivate the need for sophisticated methods for correlated and finite data that follow complex processes. The importance of extremes has been rapidly growing in areas ranging from climate change and critical infrastructures to insurance and financial markets. Here we briefly discuss the state-of-the-art and key gaps, through the case of rainfall extremes under climate change. Preliminary analysis suggests new directions and points to research areas that deserve further attention.

Details

ECAI Conference 2010 Conference Paper

Regression Learning with Multiple Noisy Oracles

Kosta Ristovski
Debasish Das
Vladimir Ouzienko
Yuhong Guo
Zoran Obradovic

In regression learning, it is often difficult to obtain the true values of the label variables, while multiple sources of noisy estimates of lower quality are readily available. To address this problem, we propose a new Bayesian approach that learns a regression model from data with noisy labels provided by multiple oracles. The proposed method provides closed form solution for model parameters and is applicable to both linear and nonlinear regression problems. In our experiments on synthetic and benchmark datasets this new regression model was consistently more accurate than a model trained with averaged estimates from multiple oracles as labels.

Details