activity
20162021
most citedMonitoring and explainability of models in production

29 citations · 41 across the 4 of their papers we have counts for

collaborators

8 papers

stat.ME2021

Sequential Multivariate Change Detection with Calibrated and Memoryless False Detection Rates

Oliver Cobb, Arnaud Van Looveren, Janis Klaise

Responding appropriately to the detections of a sequential change detector requires knowledge of the rate at which false positives occur in the absence of change. Setting detection…

cs.LG2021★ 3 cited

Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning

Robert-Florian Samoilescu, Arnaud Van Looveren, Janis Klaise

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the…

cs.LG2021★ 7 cited

Conditional Generative Models for Counterfactual Explanations

Arnaud Van Looveren, Janis Klaise, Giovanni Vacanti +1

Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution c…

stat.ML2020★ 29 cited

Monitoring and explainability of models in production

Janis Klaise, Arnaud Van Looveren, Clive Cox +2

The machine learning lifecycle extends beyond the deployment stage. Monitoring deployed models is crucial for continued provision of high quality machine learning enabled services.…

stat.ML2020

Practical Bayesian Optimization of Objectives with Conditioning Variables

Michael Pearce, Janis Klaise, Matthew Groves

Bayesian optimization is a class of data efficient model based algorithms typically focused on global optimization. We consider the more general case where a user is faced with mul…

cs.LG2019

Interpretable Counterfactual Explanations Guided by Prototypes

Arnaud Van Looveren, Janis Klaise

We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, o…