Screening is important for the diagnosis and treatment of a wide variety of diseases. A good screening policy should be personalized to the features of the patient and to the dynamic history of the patient (including the history of screening).

Early Classification of Time Series (ECTS) has been recognized as an important problem in many areas where decisions have to be taken as soon as possible, before the full data availability, while time pressure increases. Numerous ECTS approaches have been proposed, based on different triggering functions, each taking into account various pieces of information related to the incoming time series and/or the output of a classifier. Although their performances have been empirically compared in the literature, no studies have been carried out on the optimality of these triggering functions that involve ``man-tailored'' decision rules. Based on the same information, could there be better triggering functions? This paper presents one way to investigate this question by showing first how to translate ECTS problems into Reinforcement Learning (RL) ones, where the very same information is used in the state space. A thorough comparison of the performance obtained by ``handmade'' approaches and their ``RL-based'' counterparts has been carried out. A second question investigated in this paper is whether a different combination of information, defining the state space in RL systems, can achieve even better performance. Experiments show that the system we describe, called \textsc{Alert}, significantly outperforms its state-of-the-art competitors on a large number of datasets.

Screening is important for the diagnosis and treatment of a wide variety of diseases. A good screening policy should be personalized to the features of the patient and to the dynamic history of the patient (including the history of screening). The growth of electronic health records data has led to the development of many models to predict the onset and progression of different diseases. However, there has been limited work to address the personalized screening for these different diseases. In this work, we develop the first framework to construct screening policies for a large class of disease models.

We revisit the online dynamic acknowledgment problem. In the problem, a sequence of requests arrive over time to be acknowledged, and all outstanding requests can be satisfied simultaneously by one acknowledgement. The goal of the problem is to minimize the total request delay plus acknowledgement cost. This elegant model studies the trade-off between acknowledgement cost and waiting experienced by requests. The problem has been well studied and the tight competitive ratios have been determined. For this well-studied problem, we focus on how to effectively use machine-learned predictions to have better performance. We develop algorithms that perform arbitrarily close to the optimum with accurate predictions while concurrently having the guarantees arbitrarily close to what the best online algorithms can offer without access to predictions, thereby achieving simultaneous optimum consistency and robustness. This new result is enabled by our novel prediction error measure. No error measure was defined for the problem prior to our work, and natural measures failed due to the challenge that requests with different arrival times have different effects on the objective. We hope our ideas can be used for other online problems with temporal aspects that have been resisting proper error measures.

They have been widely implemented in applications, including video frame inpainting [33] and automatic driving [31]. The performance of neural networks is mainly affected by hyperparameter selection and network topology. Hyperparameter selection [3, 4] is a classical topic in machine learning, which can be realized by grid search [26, 32] and particle swarm optimization [1, 24]. In addition, network topology [2, 30, 42] is the key of neural network design, which can be realized through three-way decisions [7] and an incremental learning mechanism [10, 15, 40]. To achieve an effective network structure, three-way decisions with a single hidden layer feedforward neural network (TWD-SFNN) [7] adopts a novel model to guide the number of hidden layer nodes. In addition, as a shallow neural network model, TWD-SFNN provides a new perspective for the topology design of multilayer neural networks, hence laying the theoretical foundation for the framework of deep learning. However, for practical applications, TWD-SFNN has two drawbacks: (i) in terms of the performance of TWD-SFNN, the generalization ability of TWD-SFNN needs to be further improved; and (ii) to analyze the relationship between the costs and number of hidden layer nodes more thoroughly, the process costs of TWD-SFNN need to be considered. To improve the generalization ability of neural networks on structured datasets, and further enrich the theoretical framework of deep learning, we employ sequential three-way decisions to guide the growth of the network topology.

Screening is important for the diagnosis and treatment of a wide variety of diseases. A good screening policy should be personalized to the disease, to the features of the patient and to the dynamic history of the patient (including the history of screening). The growth of electronic health records data has led to the development of many models to predict the onset and progression of different diseases. However, there has been limited work to address the personalized screening for these different diseases. In this work, we develop the first framework to construct screening policies for a large class of disease models. The disease is modeled as a finite state stochastic process with an absorbing disease state. The patient observes an external information process (for instance, self-examinations, discovering comorbidities, etc.) which can trigger the patient to arrive at the clinician earlier than scheduled screenings. The clinician carries out the tests; based on the test results and the external information it schedules the next arrival. Computing the exactly optimal screening policy that balances the delay in the detection against the frequency of screenings is computationally intractable; this paper provides a computationally tractable construction of an approximately optimal policy. As an illustration, we make use of a large breast cancer data set. The constructed policy screens patients more or less often according to their initial risk -- it is personalized to the features of the patient -- and according to the results of previous screens – it is personalized to the history of the patient. In comparison with existing clinical policies, the constructed policy leads to large reductions (28-68 %) in the number of screens performed while achieving the same expected delays in disease detection.