350 citations · 652 across the 49 of their papers we have counts for
9 papers · 1 filter
Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties
Yassir Fathullah, Guoxuan Xia, Mark Gales
Efficiently and reliably estimating uncertainty is an important objective in deep learning. It is especially pertinent to autoregressive sequence tasks, where training and inferenc…
Identifying Adversarially Attackable and Robust Samples
Vyas Raina, Mark Gales
Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research…
Shifts 2.0: Extending The Dataset of Real Distributional Shifts
Andrey Malinin, Andreas Athanasopoulos, Muhamed Barakovic +15
Distributional shift, or the mismatch between training and deployment data, is a significant obstacle to the usage of machine learning in high-stakes industrial applications, such…
Self-Distribution Distillation: Efficient Uncertainty Estimation
Yassir Fathullah, Mark J. F. Gales
Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model's prediction to ensure appro…
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Andrey Malinin, Neil Band, Ganshin +17
There has been significant research done on developing methods for improving robustness to distributional shift and uncertainty estimation. In contrast, only limited work has exami…
Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets
Max Ryabinin, Andrey Malinin, Mark Gales
Ensembles of machine learning models yield improved system performance as well as robust and interpretable uncertainty estimates; however, their inference costs may often be prohib…
Should Ensemble Members Be Calibrated?
Xixin Wu, Mark Gales
Underlying the use of statistical approaches for a wide range of applications is the assumption that the probabilities obtained from a statistical model are representative of the "…
Regression Prior Networks
Andrey Malinin, Sergey Chervontsev, Ivan Provilkov +1
Prior Networks are a recently developed class of models which yield interpretable measures of uncertainty and have been shown to outperform state-of-the-art ensemble approaches on…
Attention Forcing for Sequence-to-sequence Model Training
Qingyun Dou, Yiting Lu, Joshua Efiong +1
Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. Thes…