no code implementations • 18 Jan 2024 • Ioana Bica, Anastasija Ilić, Matthias Bauer, Goker Erdogan, Matko Bošnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrović
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs.
2 code implementations • NeurIPS 2021 • Ioana Bica, Daniel Jarrett, Mihaela van der Schaar
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.
no code implementations • NeurIPS 2021 • Daniel Jarrett, Ioana Bica, Mihaela van der Schaar
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.
1 code implementation • ICLR 2021 • Daniel Jarrett, Jinsung Yoon, Ioana Bica, Zhaozhi Qian, Ari Ercole, Mihaela van der Schaar
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.
no code implementations • 20 Feb 2023 • Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković
We evaluate our method on the CLRS algorithmic reasoning benchmark, where we show up to 3$\times$ improvements on the OOD test data.
2 code implementations • 24 Oct 2022 • Nabeel Seedat, Jonathan Crabbé, Ioana Bica, Mihaela van der Schaar
High model performance, on average, can hide that models may systematically underperform on subgroups of the data.
2 code implementations • 8 Oct 2022 • Ioana Bica, Mihaela van der Schaar
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.
no code implementations • 2 Aug 2022 • Yanke Li, Hatt Tobias, Ioana Bica, Mihaela van der Schaar
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 $E$.
no code implementations • 16 Jun 2022 • Jonathan Crabbé, Alicia Curth, Ioana Bica, Mihaela van der Schaar
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.
no code implementations • 13 Jan 2022 • Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
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
no code implementations • 7 Dec 2021 • Jeroen Berrevoets, Alicia Curth, Ioana Bica, Eoin McKinney, Mihaela van der Schaar
Choosing the best treatment-plan for each individual patient requires accurate forecasts of their outcome trajectories as a function of the treatment, over time.
1 code implementation • NeurIPS 2021 • Zhaozhi Qian, Yao Zhang, Ioana Bica, Angela Wood, Mihaela van der Schaar
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.
1 code implementation • 8 Jun 2021 • Alex J. Chan, Ioana Bica, Alihan Huyuk, Daniel Jarrett, Mihaela van der Schaar
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.
no code implementations • 23 Feb 2021 • Victor D. Bourgin, Ioana Bica, Mihaela van der Schaar
Medical time-series datasets have unique characteristics that make prediction tasks challenging.
no code implementations • 11 Feb 2021 • Trent Kyono, Ioana Bica, Zhaozhi Qian, Mihaela van der Schaar
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.
1 code implementation • 28 Jan 2021 • Can Xu, Ahmed M. Alaa, Ioana Bica, Brent D. Ershoff, Maxime Cannesson, Mihaela van der Schaar
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.
no code implementations • 1 Jan 2021 • Zhaozhi Qian, Yao Zhang, Ioana Bica, Angela Wood, Mihaela van der Schaar
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.
no code implementations • NeurIPS 2020 • Jeroen Berrevoets, James Jordon, Ioana Bica, alexander gimson, Mihaela van der Schaar
Transplant-organs are a scarce medical resource.
no code implementations • ICLR 2021 • Ioana Bica, Daniel Jarrett, Alihan Hüyük, Mihaela van der Schaar
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.
1 code implementation • NeurIPS 2020 • Daniel Jarrett, Ioana Bica, Mihaela van der Schaar
Through experiments with application to control and healthcare settings, we illustrate consistent performance gains over existing algorithms for strictly batch imitation learning.
1 code implementation • NeurIPS 2020 • Ioana Bica, James Jordon, Mihaela van der Schaar
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.
3 code implementations • ICLR 2020 • Ioana Bica, Ahmed M. Alaa, James Jordon, Mihaela van der Schaar
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.
no code implementations • ICLR 2020 • Ioana Bica, James Jordon, Mihaela van der Schaar
Our model consists of 3 blocks: (1) a generator, (2) a discriminator, (3) an inference block.
2 code implementations • ICML 2020 • Ioana Bica, Ahmed M. Alaa, Mihaela van der Schaar
The estimation of treatment effects is a pervasive problem in medicine.