research
∙
07/18/2023
Conformal prediction under ambiguous ground truth
In safety-critical classification tasks, conformal prediction allows to ...
share
research
∙
07/05/2023
Evaluating AI systems under uncertain ground truth: a case study in dermatology
For safety, AI systems in health undergo thorough evaluations before dep...
research
∙
01/31/2023
Transformers Meet Directed Graphs
Transformers were originally proposed as a sequence-to-sequence model fo...
research
∙
10/18/2021
Learning Optimal Conformal Classifiers
Modern deep learning based classifiers show very high accuracy on test d...
research
∙
12/20/2020
Towards Fair Personalization by Avoiding Feedback Loops
Self-reinforcing feedback loops are both cause and effect of over and/or...
research
∙
10/04/2020
Intermittent Demand Forecasting with Renewal Processes
Intermittency is a common and challenging problem in demand forecasting....
research
∙
08/15/2019
A Bayesian Choice Model for Eliminating Feedback Loops
Self-reinforcing feedback loops in personalization systems are typically...
research
∙
03/11/2019
Bayesian Allocation Model: Inference by Sequential Monte Carlo for Nonnegative Tensor Factorizations and Topic Models using Polya Urns
We introduce a dynamic generative model, Bayesian allocation model (BAM)...
research
∙
10/31/2018
Weak Label Supervision For Monaural Source Separation Using Non-negative Denoising Variational Autoencoders
Deep learning models are very effective in source separation when there ...
research
∙
11/30/2017
Differentially Private Variational Dropout
Deep neural networks with their large number of parameters are highly fl...
research
∙
11/30/2017
Differentially Private Dropout
Large data collections required for the training of neural networks ofte...
research
∙
10/01/2013
