%0 Journal Article %1 vadera2020ursabench %A Vadera, Meet P. %A Cobb, Adam D. %A Jalaian, Brian %A Marlin, Benjamin M. %D 2020 %K bayesian benchmarks deep-learning readings %T URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks %U http://arxiv.org/abs/2007.04466 %X While deep learning methods continue to improve in predictive accuracy on a wide range of application domains, significant issues remain with other aspects of their performance including their ability to quantify uncertainty and their robustness. Recent advances in approximate Bayesian inference hold significant promise for addressing these concerns, but the computational scalability of these methods can be problematic when applied to large-scale models. In this paper, we describe initial work on the development ofURSABench(the Uncertainty, Robustness, Scalability, and Accu-racy Benchmark), an open-source suite of bench-marking tools for comprehensive assessment of approximate Bayesian inference methods with a focus on deep learning-based classification tasks

@article{vadera2020ursabench, abstract = {While deep learning methods continue to improve in predictive accuracy on a wide range of application domains, significant issues remain with other aspects of their performance including their ability to quantify uncertainty and their robustness. Recent advances in approximate Bayesian inference hold significant promise for addressing these concerns, but the computational scalability of these methods can be problematic when applied to large-scale models. In this paper, we describe initial work on the development ofURSABench(the Uncertainty, Robustness, Scalability, and Accu-racy Benchmark), an open-source suite of bench-marking tools for comprehensive assessment of approximate Bayesian inference methods with a focus on deep learning-based classification tasks}, added-at = {2020-07-16T11:43:16.000+0200}, author = {Vadera, Meet P. and Cobb, Adam D. and Jalaian, Brian and Marlin, Benjamin M.}, biburl = {https://www.bibsonomy.org/bibtex/28d797b218d4f61ccae514c6f29094e09/kirk86}, description = {[2007.04466] URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks}, interhash = {5f64b01287b7af61a9f394bb7704b487}, intrahash = {8d797b218d4f61ccae514c6f29094e09}, keywords = {bayesian benchmarks deep-learning readings}, note = {cite arxiv:2007.04466Comment: Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning}, timestamp = {2020-07-16T11:43:16.000+0200}, title = {URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks}, url = {http://arxiv.org/abs/2007.04466}, year = 2020 }