arXiv subjects

Mihaela van der Schaar

Publications and source records attributed to Mihaela van der Schaar.

At least 235 records · Page 13Linked to original sources

arXiv2020

When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes

The coronavirus disease 2019 (COVID-19) global pandemic has led many countries to impose unprecedented lockdown measures in order to slow down the outbreak. Questions on whether governments have acted promptly enough, and whether lockdown measures can be lifted soon have since been central in public discourse. Data-driven models that predict COVID-19 fatalities under different lockdown policy scenarios are essential for addressing these questions and informing governments on future policy directions. To this end, this paper develops a Bayesian model for predicting the effects of COVID-19 lockdown policies in a global context -- we treat each country as a distinct data point, and exploit variations of policies across countries to learn country-specific policy effects. Our model utilizes a two-layer Gaussian process (GP) prior -- the lower layer uses a compartmental SEIR (Susceptible, Exposed, Infected, Recovered) model as a prior mean function with "country-and-policy-specific" parameters that capture fatality curves under "counterfactual" policies within each country, whereas the upper layer is shared across all countries, and learns lower-layer SEIR parameters as a function of a country's features and its policy indicators. Our model combines the solid mechanistic foundations of SEIR models (Bayesian priors) with the flexible data-driven modeling and gradient-based optimization routines of machine learning (Bayesian posteriors) -- i.e., the entire model is trained end-to-end via stochastic variational inference. We compare the projections of COVID-19 fatalities by our model with other models listed by the Center for Disease Control (CDC), and provide scenario analyses for various lockdown and reopening strategies highlighting their impact on COVID-19 fatalities.

stat.AP↗

arXiv2020

A primer on coupled state-switching models for multiple interacting time series

State-switching models such as hidden Markov models or Markov-switching regression models are routinely applied to analyse sequences of observations that are driven by underlying non-observable states. Coupled state-switching models extend these approaches to address the case of multiple observation sequences whose underlying state variables interact. In this paper, we provide an overview of the modelling techniques related to coupling in state-switching models, thereby forming a rich and flexible statistical framework particularly useful for modelling correlated time series. Simulation experiments demonstrate the relevance of being able to account for an asynchronous evolution as well as interactions between the underlying latent processes. The models are further illustrated using two case studies related to a) interactions between a dolphin mother and her calf as inferred from movement data; and b) electronic health record data collected on 696 patients within an intensive care unit.

stat.ME↗

arXiv2020

A Non-Stationary Bandit-Learning Approach to Energy-Efficient Femto-Caching with Rateless-Coded Transmission

The ever-increasing demand for media streaming together with limited backhaul capacity renders developing efficient file-delivery methods imperative. One such method is femto-caching, which, despite its great potential, imposes several challenges such as efficient resource management. We study a resource allocation problem for joint caching and transmission in small cell networks, where the system operates in two consecutive phases: (i) cache placement, and (ii) joint file- and transmit power selection followed by broadcasting. We define the utility of every small base station in terms of the number of successful reconstructions per unit of transmission power. We then formulate the problem as to select a file from the cache together with a transmission power level for every broadcast round so that the accumulated utility over the horizon is maximized. The former problem boils down to a stochastic knapsack problem, and we cast the latter as a multi-armed bandit problem. We develop a solution to each problem and provide theoretical and numerical evaluations. In contrast to the state-of-the-art research, the proposed approach is especially suitable for networks with time-variant statistical properties. Moreover, it is applicable and operates well even when no initial information about the statistical characteristics of the random parameters such as file popularity and channel quality is available.

eess.SP↗

arXiv2020

Contextual Constrained Learning for Dose-Finding Clinical Trials

Clinical trials in the medical domain are constrained by budgets. The number of patients that can be recruited is therefore limited. When a patient population is heterogeneous, this creates difficulties in learning subgroup specific responses to a particular drug and especially for a variety of dosages. In addition, patient recruitment can be difficult by the fact that clinical trials do not aim to provide a benefit to any given patient in the trial. In this paper, we propose C3T-Budget, a contextual constrained clinical trial algorithm for dose-finding under both budget and safety constraints. The algorithm aims to maximize drug efficacy within the clinical trial while also learning about the drug being tested. C3T-Budget recruits patients with consideration of the remaining budget, the remaining time, and the characteristics of each group, such as the population distribution, estimated expected efficacy, and estimation credibility. In addition, the algorithm aims to avoid unsafe dosages. These characteristics are further illustrated in a simulated clinical trial study, which corroborates the theoretical analysis and demonstrates an efficient budget usage as well as a balanced learning-treatment trade-off.

stat.ML↗

arXiv2020

Learning Overlapping Representations for the Estimation of Individualized Treatment Effects

The choice of making an intervention depends on its potential benefit or harm in comparison to alternatives. Estimating the likely outcome of alternatives from observational data is a challenging problem as all outcomes are never observed, and selection bias precludes the direct comparison of differently intervened groups. Despite their empirical success, we show that algorithms that learn domain-invariant representations of inputs (on which to make predictions) are often inappropriate, and develop generalization bounds that demonstrate the dependence on domain overlap and highlight the need for invertible latent maps. Based on these results, we develop a deep kernel regression algorithm and posterior regularization framework that substantially outperforms the state-of-the-art on a variety of benchmarks data sets.

stat.ML↗

arXiv2020

Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning

An essential problem in automated machine learning (AutoML) is that of model selection. A unique challenge in the sequential setting is the fact that the optimal model itself may vary over time, depending on the distribution of features and labels available up to each point in time. In this paper, we propose a novel Bayesian optimization (BO) algorithm to tackle the challenge of model selection in this setting. This is accomplished by treating the performance at each time step as its own black-box function. In order to solve the resulting multiple black-box function optimization problem jointly and efficiently, we exploit potential correlations among black-box functions using deep kernel learning (DKL). To the best of our knowledge, we are the first to formulate the problem of stepwise model selection (SMS) for sequence prediction, and to design and demonstrate an efficient joint-learning algorithm for this purpose. Using multiple real-world datasets, we verify that our proposed method outperforms both standard BO and multi-objective BO algorithms on a variety of sequence prediction tasks.

cs.LG↗

arXiv2020

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. In this paper, we introduce the Counterfactual Recurrent Network (CRN), a novel sequence-to-sequence model that leverages the increasingly available patient observational data to estimate treatment effects over time and answer such medical questions. To handle the bias from time-varying confounders, covariates affecting the treatment assignment policy in the observational data, CRN uses domain adversarial training to build balancing representations of the patient history. At each timestep, CRN constructs a treatment invariant representation which removes the association between patient history and treatment assignments and thus can be reliably used for making counterfactual predictions. On a simulated model of tumour growth, with varying degree of time-dependent confounding, we show how our model achieves lower error in estimating counterfactuals and in choosing the correct treatment and timing of treatment than current state-of-the-art methods.

cs.LG↗

arXiv2020

Target-Embedding Autoencoders for Supervised Representation Learning

Autoencoder-based learning has emerged as a staple for disciplining representations in unsupervised and semi-supervised settings. This paper analyzes a framework for improving generalization in a purely supervised setting, where the target space is high-dimensional. We motivate and formalize the general framework of target-embedding autoencoders (TEA) for supervised prediction, learning intermediate latent representations jointly optimized to be both predictable from features as well as predictive of targets---encoding the prior that variations in targets are driven by a compact set of underlying factors. As our theoretical contribution, we provide a guarantee of generalization for linear TEAs by demonstrating uniform stability, interpreting the benefit of the auxiliary reconstruction task as a form of regularization. As our empirical contribution, we extend validation of this approach beyond existing static classification applications to multivariate sequence forecasting, verifying their advantage on both linear and nonlinear recurrent architectures---thereby underscoring the further generality of this framework beyond feedforward instantiations.

stat.ML↗

arXiv2020

Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes

Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic health records we can observe the different diseases a patient has, but can only infer the temporal relationship between each co-morbid condition. Learning such temporal patterns from event data is crucial for understanding disease pathology and predicting prognoses. To this end, we develop deep diffusion processes (DDP) to model "dynamic comorbidity networks", i.e., the temporal relationships between comorbid disease onsets expressed through a dynamic graph. A DDP comprises events modelled as a multi-dimensional point process, with an intensity function parameterized by the edges of a dynamic weighted graph. The graph structure is modulated by a neural network that maps patient history to edge weights, enabling rich temporal representations for disease trajectories. The DDP parameters decouple into clinically meaningful components, which enables serving the dual purpose of accurate risk prediction and intelligible representation of disease pathology. We illustrate these features in experiments using cancer registry data.

cs.LG↗

arXiv2019

A Bayesian Approach to Modelling Longitudinal Data in Electronic Health Records

Analyzing electronic health records (EHR) poses significant challenges because often few samples are available describing a patient's health and, when available, their information content is highly diverse. The problem we consider is how to integrate sparsely sampled longitudinal data, missing measurements informative of the underlying health status and fixed demographic information to produce estimated survival distributions updated through a patient's follow up. We propose a nonparametric probabilistic model that generates survival trajectories from an ensemble of Bayesian trees that learns variable interactions over time without specifying beforehand the longitudinal process. We show performance improvements on Primary Biliary Cirrhosis patient data.

stat.ML↗

arXiv2019

Conditional Independence Testing using Generative Adversarial Networks

We consider the hypothesis testing problem of detecting conditional dependence, with a focus on high-dimensional feature spaces. Our contribution is a new test statistic based on samples from a generative adversarial network designed to approximate directly a conditional distribution that encodes the null hypothesis, in a manner that maximizes power (the rate of true negatives). We show that such an approach requires only that density approximation be viable in order to ensure that we control type I error (the rate of false positives); in particular, no assumptions need to be made on the form of the distributions or feature dependencies. Using synthetic simulations with high-dimensional data we demonstrate significant gains in power over competing methods. In addition, we illustrate the use of our test to discover causal markers of disease in genetic data.

stat.ML↗

arXiv2019

Improving Model Robustness Using Causal Knowledge

For decades, researchers in fields, such as the natural and social sciences, have been verifying causal relationships and investigating hypotheses that are now well-established or understood as truth. These causal mechanisms are properties of the natural world, and thus are invariant conditions regardless of the collection domain or environment. We show in this paper how prior knowledge in the form of a causal graph can be utilized to guide model selection, i.e., to identify from a set of trained networks the models that are the most robust and invariant to unseen domains. Our method incorporates prior knowledge (which can be incomplete) as a Structural Causal Model (SCM) and calculates a score based on the likelihood of the SCM given the target predictions of a candidate model and the provided input variables. We show on both publicly available and synthetic datasets that our method is able to identify more robust models in terms of generalizability to unseen out-of-distribution test examples and domains where covariates have shifted.

cs.LG↗

arXiv2019

Dynamic Matching and Allocation of Tasks

In many two-sided markets, the parties to be matched have incomplete information about their characteristics. We consider the settings where the parties engaged are extremely patient and are interested in long-term partnerships. Hence, once the final matches are determined, they persist for a long time. Each side has an opportunity to learn (some) relevant information about the other before final matches are made. For instance, clients seeking workers to perform tasks often conduct interviews that require the workers to perform some tasks and thereby provide information to both sides. The performance of a worker in such an interview- and hence the information revealed - depends both on the inherent characteristics of the worker and the task and also on the actions taken by the worker (e.g. the effort expended), which are not observed by the client. Thus there is moral hazard. Our goal is to derive a dynamic matching mechanism that facilitates learning on both sides before final matches are achieved and ensures that the worker side does not have incentive to obscure learning of their characteristics through their actions. We derive such a mechanism that leads to final matching that achieve optimal performance (revenue) in equilibrium. We show that the equilibrium strategy is long-run coalitionally stable, which means there is no subset of workers and clients that can gain by deviating from the equilibrium strategy. We derive all the results under the modeling assumption that the utilities of the agents are defined as limit of means of the utility obtained in each interaction.

cs.GT↗

arXiv2019

Optimal Piecewise Local-Linear Approximations

Existing works on "black-box" model interpretation use local-linear approximations to explain the predictions made for each data instance in terms of the importance assigned to the different features for arriving at the prediction. These works provide instancewise explanations and thus give a local view of the model. To be able to trust the model it is important to understand the global model behavior and there are relatively fewer works which do the same. Piecewise local-linear models provide a natural way to extend local-linear models to explain the global behavior of the model. In this work, we provide a dynamic programming based framework to obtain piecewise approximations of the black-box model. We also provide provable fidelity, i.e., how well the explanations reflect the black-box model, guarantees. We carry out simulations on synthetic and real datasets to show the utility of the proposed approach. At the end, we show that the ideas developed for our framework can also be used to address the problem of clustering for one-dimensional data. We give a polynomial time algorithm and prove that it achieves optimal clustering.

cs.LG↗

arXiv2019

Joint Concordance Index

Existing metrics in competing risks survival analysis such as concordance and accuracy do not evaluate a model's ability to jointly predict the event type and the event time. To address these limitations, we propose a new metric, which we call the joint concordance. The joint concordance measures a model's ability to predict the overall risk profile, i.e., risk of death from different event types. We develop a consistent estimator for the new metric that accounts for the censoring bias. We use the new metric to develop a variable importance ranking approach. Using the real and synthetic data experiments, we show that models selected using the existing metrics are worse than those selected using joint concordance at jointly predicting the event type and event time. We show that the existing approaches for variable importance ranking often fail to recognize the importance of the event-specific risk factors, whereas, the proposed approach does not, since it compares risk factors based on their contribution to the prediction of the different event-types. To summarize, joint concordance is helpful for model comparisons and variable importance ranking and has the potential to impact applications such as risk-stratification and treatment planning in multimorbid populations.

stat.ME↗

arXiv2019

Lifelong Bayesian Optimization

Automatic Machine Learning (Auto-ML) systems tackle the problem of automating the design of prediction models or pipelines for data science. In this paper, we present Lifelong Bayesian Optimization (LBO), an online, multitask Bayesian optimization (BO) algorithm designed to solve the problem of model selection for datasets arriving and evolving over time. To be suitable for "lifelong" Bayesian Optimization, an algorithm needs to scale with the ever increasing number of acquisitions and should be able to leverage past optimizations in learning the current best model. We cast the problem of model selection as a black-box function optimization problem. In LBO, we exploit the correlation between functions by using components of previously learned functions to speed up the learning process for newly arriving datasets. Experiments on real and synthetic data show that LBO outperforms standard BO algorithms applied repeatedly on the data.

stat.ML↗

arXiv2019

ASAC: Active Sensing using Actor-Critic models

Deciding what and when to observe is critical when making observations is costly. In a medical setting where observations can be made sequentially, making these observations (or not) should be an active choice. We refer to this as the active sensing problem. In this paper, we propose a novel deep learning framework, which we call ASAC (Active Sensing using Actor-Critic models) to address this problem. ASAC consists of two networks: a selector network and a predictor network. The selector network uses previously selected observations to determine what should be observed in the future. The predictor network uses the observations selected by the selector network to predict a label, providing feedback to the selector network (well-selected variables should be predictive of the label). The goal of the selector network is then to select variables that balance the cost of observing the selected variables with their predictive power; we wish to preserve the conditional label distribution. During training, we use the actor-critic models to allow the loss of the selector to be "back-propagated" through the sampling process. The selector network "acts" by selecting future observations to make. The predictor network acts as a "critic" by feeding predictive errors for the selected variables back to the selector network. In our experiments, we show that ASAC significantly outperforms state-of-the-arts in two real-world medical datasets.

cs.LG↗

arXiv2019

What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems

Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees, are inherently human-interpretable, which has not been empirically tested. Additionally, past efforts have focused exclusively on comprehension, neglecting to explore the trust component necessary to convince non-technical experts, such as clinicians, to utilize ML models in practice. In this paper, we posit that reinforcement learning (RL) can be used to learn what is interpretable to different users and, consequently, build their trust in ML models. To validate this idea, we first train a neural network to provide risk assessments for heart failure patients. We then design a RL-based clinical decision-support system (DSS) around the neural network model, which can learn from its interactions with users. We conduct an experiment involving a diverse set of clinicians from multiple institutions in three different countries. Our results demonstrate that ML experts cannot accurately predict which system outputs will maximize clinicians' confidence in the underlying neural network model, and suggest additional findings that have broad implications to the future of research into ML interpretability and the use of ML in medicine.

cs.LG↗