Search Results for author:
Found 24 papers, 11 papers with code
Strictly Batch Imitation Learning by Energy-based Distribution Matching
Through experiments with application to control and healthcare settings, we illustrate consistent performance gains over existing algorithms for strictly batch imitation learning.
Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Consider the problem of improving the estimation of conditional average treatment effects (CATE) for a target domain of interest by leveraging related information from a source domain with a different feature space.
Invariant Causal Imitation Learning for Generalizable Policies
By leveraging data from multiple environments, we propose Invariant Causal Imitation Learning (ICIL), a novel technique in which we learn a feature representation that is invariant across domains, on the basis of which we learn an imitation policy that matches expert behavior.
Clairvoyance: A Pipeline Toolkit for Medical Time Series
Despite exponential growth in electronic patient data, there is a remarkable gap between the potential and realized utilization of ML for clinical research and decision support.
Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations
Identifying when to give treatments to patients and how to select among multiple treatments over time are important medical problems with a few existing solutions.
Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders
The estimation of treatment effects is a pervasive problem in medicine.
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks
While much attention has been given to the problem of estimating the effect of discrete interventions from observational data, relatively little work has been done in the setting of continuous-valued interventions, such as treatments associated with a dosage parameter.
The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation
Understanding decision-making in clinical environments is of paramount importance if we are to bring the strengths of machine learning to ultimately improve patient outcomes.
Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
High model performance, on average, can hide that models may systematically underperform on subgroups of the data.
SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes
Most of the medical observational studies estimate the causal treatment effects using electronic health records (EHR), where a patient's covariates and outcomes are both observed longitudinally.
Learning Matching Representations for Individualized Organ Transplantation Allocation
Organ transplantation is often the last resort for treating end-stage illness, but the probability of a successful transplantation depends greatly on compatibility between donors and recipients.
Individualised Dose-Response Estimation using Generative Adversarial Nets
Our model consists of 3 blocks: (1) a generator, (2) a discriminator, (3) an inference block.
Learning "What-if" Explanations for Sequential Decision-Making
Building interpretable parameterizations of real-world decision-making on the basis of demonstrated behavior -- i. e. trajectories of observations and actions made by an expert maximizing some unknown reward function -- is essential for introspecting and auditing policies in different institutions.
SyncTwin: Transparent Treatment Effect Estimation under Temporal Confounding
Estimating causal treatment effects using observational data is a problem with few solutions when the confounder has a temporal structure, e. g. the history of disease progression might impact both treatment decisions and clinical outcomes.
OrganITE: Optimal transplant donor organ offering using an individual treatment effect
Transplant-organs are a scarce medical resource.
Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledge
We leverage the invariance of causal structures across domains to propose a novel model selection metric specifically designed for ITE methods under the UDA setting.
Model-Attentive Ensemble Learning for Sequence Modeling
Medical time-series datasets have unique characteristics that make prediction tasks challenging.
Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time
Choosing the best treatment-plan for each individual patient requires accurate forecasts of their outcome trajectories as a function of the treatment, over time.
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Most notably, ReLICv2 is the first unsupervised representation learning method to consistently outperform the supervised baseline in a like-for-like comparison over a range of ResNet architectures.
Ranked #14 on
Semantic Segmentation
on PASCAL VOC 2012 val
Representation Learning
Self-Supervised Image Classification
+3
Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
This allows us to evaluate treatment effect estimators along a new and important dimension that has been overlooked in previous work: We construct a benchmarking environment to empirically investigate the ability of personalized treatment effect models to identify predictive covariates -- covariates that determine differential responses to treatment.
DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction
The encoder is designed to serve as an inference device on $E$ while the decoder reconstructs each observed variable conditioned on its graphical parents in the DAG and the inferred $E$.
Neural Algorithmic Reasoning with Causal Regularisation
We evaluate our method on the CLRS algorithmic reasoning benchmark, where we show up to 3$\times$ improvements on the OOD test data.
Time-series Generation by Contrastive Imitation
In this work, we study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy, where the reinforcement signal is provided by a global (but stepwise-decomposable) energy model trained by contrastive estimation.
Improving fine-grained understanding in image-text pre-training
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs.
