Alert button
Picture for Mihaela van der Schaar

Mihaela van der Schaar

Alert button

Data-SUITE: Data-centric identification of in-distribution incongruous examples

Feb 17, 2022
Nabeel Seedat, Jonathan Crabbe, Mihaela van der Schaar

Figure 1 for Data-SUITE: Data-centric identification of in-distribution incongruous examples
Figure 2 for Data-SUITE: Data-centric identification of in-distribution incongruous examples
Figure 3 for Data-SUITE: Data-centric identification of in-distribution incongruous examples
Figure 4 for Data-SUITE: Data-centric identification of in-distribution incongruous examples
Viaarxiv icon

To Impute or not to Impute? -- Missing Data in Treatment Effect Estimation

Feb 04, 2022
Jeroen Berrevoets, Fergus Imrie, Trent Kyono, James Jordon, Mihaela van der Schaar

Figure 1 for To Impute or not to Impute? -- Missing Data in Treatment Effect Estimation
Figure 2 for To Impute or not to Impute? -- Missing Data in Treatment Effect Estimation
Figure 3 for To Impute or not to Impute? -- Missing Data in Treatment Effect Estimation
Figure 4 for To Impute or not to Impute? -- Missing Data in Treatment Effect Estimation
Viaarxiv icon

Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time

Dec 07, 2021
Jeroen Berrevoets, Alicia Curth, Ioana Bica, Eoin McKinney, Mihaela van der Schaar

Figure 1 for Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time
Figure 2 for Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time
Figure 3 for Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time
Figure 4 for Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time
Viaarxiv icon

MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms

Nov 04, 2021
Trent Kyono, Yao Zhang, Alexis Bellot, Mihaela van der Schaar

Figure 1 for MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms
Figure 2 for MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms
Figure 3 for MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms
Figure 4 for MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms
Viaarxiv icon

DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks

Nov 04, 2021
Boris van Breugel, Trent Kyono, Jeroen Berrevoets, Mihaela van der Schaar

Figure 1 for DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
Figure 2 for DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
Figure 3 for DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
Figure 4 for DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
Viaarxiv icon

Explaining Latent Representations with a Corpus of Examples

Oct 28, 2021
Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar

Figure 1 for Explaining Latent Representations with a Corpus of Examples
Figure 2 for Explaining Latent Representations with a Corpus of Examples
Figure 3 for Explaining Latent Representations with a Corpus of Examples
Figure 4 for Explaining Latent Representations with a Corpus of Examples
Viaarxiv icon

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

Oct 26, 2021
Alicia Curth, Changhee Lee, Mihaela van der Schaar

Figure 1 for SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data
Figure 2 for SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data
Figure 3 for SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data
Figure 4 for SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data
Viaarxiv icon

Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values

Sep 08, 2021
Mahed Abroshan, Kai Hou Yip, Cem Tekin, Mihaela van der Schaar

Figure 1 for Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
Figure 2 for Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
Figure 3 for Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
Figure 4 for Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
Viaarxiv icon

Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects

Aug 06, 2021
Yao Zhang, Jeroen Berrevoets, Mihaela van der Schaar

Figure 1 for Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects
Figure 2 for Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects
Figure 3 for Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects
Figure 4 for Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects
Viaarxiv icon