activity
20162021
most citedBeyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration

162 citations · 209 across the 6 of their papers we have counts for

collaborators

10 papers

cs.LG20214 cited

Shift Happens: Adjusting Classifiers

Theodore James Thibault Heiser, Mari-Liis Allikivi, Meelis Kull

Minimizing expected loss measured by a proper scoring rule, such as Brier score or log-loss (cross-entropy), is a common objective while training a probabilistic classifier. If the…

cs.LG2021

Instance-based Label Smoothing For Better Calibrated Classification Networks

Mohamed Maher, Meelis Kull

Label smoothing is widely used in deep neural networks for multi-class classification. While it enhances model generalization and reduces overconfidence by aiming to lower the prob…

cs.LG2020

Correlated daily time series and forecasting in the M4 competition

Anti Ingel, Novin Shahroudi, Markus Kängsepp +3

We participated in the M4 competition for time series forecasting and describe here our methods for forecasting daily time series. We used an ensemble of five statistical forecasti…

cs.LG2019162 cited

Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration

Meelis Kull, Miquel Perello-Nieto, Markus Kängsepp +3

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperatu…

cs.LG2019

HyperStream: a Workflow Engine for Streaming Data

Tom Diethe, Meelis Kull, Niall Twomey +5

This paper describes HyperStream, a large-scale, flexible and robust software package, written in the Python language, for processing streaming data with workflow creation capabili…

stat.ML20199 cited

Distribution Calibration for Regression

Hao Song, Tom Diethe, Meelis Kull +1

We are concerned with obtaining well-calibrated output distributions from regression models. Such distributions allow us to quantify the uncertainty that the model has regarding th…