作者:
He, JiananZhou, GuangquanZhou, ShoujunChen, YangSoutheast Univ
Lab Image Sci & Technol Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 210096 Peoples R China Southeast Univ
Sch Biol Sci & Med Engn State Key Lab Bioelect Nanjing 210096 Peoples R China Chinese Acad Sci
Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China Southeast Univ
Jiangsu Prov Joint Int Res Lab Med Informat Proc Sch Comp Sci & Engn Nanjing 210096 Peoples R China
Hard sample selection can effectively improve model convergence by extracting the most representative samples from a training set. However, due to the large capacity of medical images, existing sampling strategies suf...
详细信息
Hard sample selection can effectively improve model convergence by extracting the most representative samples from a training set. However, due to the large capacity of medical images, existing sampling strategies suffer from insufficient exploitation for hard samples or high time cost for sample selection when adopted by 3D patch-based models in the field of multi-organ segmentation. In this paper, we present a novel and effective online hard patch mining (OHPM) algorithm. In our method, an average shape model that can be mapped with all training images is constructed to guide the exploration of hard patches and aggregate feedback from predicted patches. The process of hard mining is formalized as a multi-armed bandit problem and solved with bandit algorithms. With the shape model, OHPM requires negligible time consumption and can intuitively locate difficult anatomical areas during training. The employment of bandit algorithms ensures online and sufficient hard mining. We integrate OHPM with advanced segmentation networks and evaluate them on two datasets containing different anatomical structures. Comparative experiments with other sampling strategies demonstrate the superiority of OHPM in boosting segmentation performance and improving model convergence. The results in each dataset with each network suggest that OHPM significantly outperforms other sampling strategies by nearly 2% average Dice score.
In this paper, we propose a method to adjust the maintenance interval of equipment by modifying the bandit algorithm. Some facilities and equipment (assembling apparatuses, generators, elevators, etc.) require mainten...
详细信息
ISBN:
(纸本)9781538663769
In this paper, we propose a method to adjust the maintenance interval of equipment by modifying the bandit algorithm. Some facilities and equipment (assembling apparatuses, generators, elevators, etc.) require maintenance or replacement to prevent failure or similar problems. Extending the interval between maintenance of the equipment increases the risk of failure but lowers maintenance costs. Our goal is to set the maintenance interval that minimizes the total cost, which is the sum of maintenance costs and the cost to fix failures. To obtain the maintenance interval that minimizes total cost, a process of trial and error is required to gather data, using an interval longer than the current interval. We consider this problem as a special bandit problem and propose a method that applies the bandit algorithm. Specifically, we regard the problem of adjusting the maintenance interval as a bandit problem with an inclusive relation in which one can know the cost of both the selected interval and also the costs of shorter intervals. As a result, the proposed method can utilize all available cost information and automatically calculate a proper maintenance interval after only a small number of trials. We perform numerical experiments with virtual scenarios and real equipment conditions and show that this method can reduce the total cost of the equipment.
This paper considers the problem of maximizing an expectation function over a finite set, or finite-arm bandit problem. We first propose a naive stochastic bandit algorithm for obtaining a probably approximately corre...
详细信息
This paper considers the problem of maximizing an expectation function over a finite set, or finite-arm bandit problem. We first propose a naive stochastic bandit algorithm for obtaining a probably approximately correct (PAC) solution to this discrete optimization problem in relative precision, that is a solution which solves the optimization problem up to a relative error smaller than a prescribed tolerance, with high probability. We also propose an adaptive stochastic bandit algorithm which provides a PAC-solution with the same guarantees. The adaptive algorithm outperforms the mean complexity of the naive algorithm in terms of number of generated samples and is particularly well suited for applications with high sampling cost.
Edge applications generate a large influx of sensor data on massive scales, and these massive data streams must be processed shortly to derive actionable intelligence. However, traditional data processing systems are ...
详细信息
Edge applications generate a large influx of sensor data on massive scales, and these massive data streams must be processed shortly to derive actionable intelligence. However, traditional data processing systems are not well-suited for these edge applications as they often do not scale well with a large number of concurrent stream queries, do not support low-latency processing under limited edge computing resources, and do not adapt to the level of heterogeneity and dynamicity commonly present in edge computing environments. As such, we present AgileDart, an agile and scalable edge stream processing engine that enables fast stream processing of many concurrently running low-latency edge applications' queries at scale in dynamic, heterogeneous edge environments. The novelty of our work lies in a dynamic dataflow abstraction that leverages distributed hash table-based peer-to-peer overlay networks to autonomously place, chain, and scale stream operators to reduce query latencies, adapt to workload variations, and recover from failures and a bandit-based path planning model that re-plans the data shuffling paths to adapt to unreliable and heterogeneous edge networks. We show that AgileDart outperforms Storm and EdgeWise on query latency and significantly improves scalability and adaptability when processing many real-world edge stream applications' queries.
Personalized pricing, which involves tailoring prices based on individual characteristics, is commonly used by firms to implement a consumer-specific pricing policy. In this process, buyers can also strategically mani...
详细信息
Personalized pricing, which involves tailoring prices based on individual characteristics, is commonly used by firms to implement a consumer-specific pricing policy. In this process, buyers can also strategically manipulate their feature data to obtain a lower price, incurring certain manipulation costs. Such strategic behavior can hinder firms from maximizing their profits. In this article, we study the contextual dynamic pricing problem with strategic buyers. The seller does not observe the buyer's true feature, but a manipulated feature according to buyers' strategic behavior. In addition, the seller does not observe the buyers' valuation of the product, but only a binary response indicating whether a sale happens or not. Recognizing these challenges, we propose a strategic dynamic pricing policy that incorporates the buyers' strategic behavior into the online learning to maximize the seller's cumulative revenue. We first prove that existing nonstrategic pricing policies that neglect the buyers' strategic behavior result in a linear Omega(T) regret with T the total time horizon, indicating that these policies are not better than a random pricing policy. We then establish an O(root T) regret upper bound of our proposed policy and an Omega(root T) regret lower bound for any pricing policy within our problem setting. This underscores the rate optimality of our policy. Importantly, our policy is not a mere amalgamation of existing dynamic pricing policies and strategic behavior handling algorithms. Our policy can also accommodate the scenario when the marginal cost of manipulation is unknown in advance. To account for it, we simultaneously estimate the valuation parameter and the cost parameter in the online pricing policy, which is shown to also achieve an Omega(root T) regret bound. Extensive experiments support our theoretical developments and demonstrate the superior performance of our policy compared to other pricing policies that are unaware of the strategic be
Existing NAS (Neural Architecture Search) algorithms achieve a low error rate on vision tasks such as image classification by training each child network with equal resources during the search. However, it is not nece...
详细信息
ISBN:
(纸本)9781665488679
Existing NAS (Neural Architecture Search) algorithms achieve a low error rate on vision tasks such as image classification by training each child network with equal resources during the search. However, it is not necessary to train with the equal resource or use the fully converge score to obtain the relative performance of each child network, and there is computational redundancy in training all child networks with the equal resource. In this paper, we propose bandit-NAS to automatically compute the required data slicing and training time for each child network. i): We first model the search of the best child network training time for a given resource into an M-armed bandit problem. ii): Then we propose a reward-flexible bandit algorithm in conjunction with existing reinforcement learning-based NAS algorithms to determine an update strategy. The proposed bandit-NAS can train M child networks simultaneously under a given resource constraint (training time for one epoch), and the amount of training data is allocated according to the current accuracy of the child networks, thus minimizing the error rate of the child networks. Experiments on CIFAR-10 show that proposed bandit-NAS performs better the baseline NAS algorithm, e.g., ENAS, with lower error rate and faster searching time.
Bid price optimization in online advertising is a challenging task due to its high uncertainty. In this paper, we propose a bid price optimization algorithm focused on keyword-level bidding for pay-per-click sponsored...
详细信息
Existing Neural Architecture Search algorithms achieve a low error rate in vision tasks, such as image classification, by training child networks with equal resources during the search. However, it is unnecessary to a...
详细信息
Existing Neural Architecture Search algorithms achieve a low error rate in vision tasks, such as image classification, by training child networks with equal resources during the search. However, it is unnecessary to allocate equal resources or fully converge scores to assess which child architectures should be adopted, resulting in computational redundancy. In this study, we present bandit-NAS, an approach that automatically computes data slicing and training time for each child network. Firstly, we formulate the search for the optimal training time for a given resource as an M -armed bandit problem. Secondly, we extend the original NAS methods by proposing an end -to -end bandit algorithm, combined with reinforcement learning -based NAS algorithms, to determine an update strategy. bandit-NAS enables simultaneous training of M child networks within a specified resource constraint (one epoch training time), with the allocation of training data based on the current accuracy of the child networks, thereby minimizing their error rate. Experimental results on 3 different datasets, MNIST , CIFAR-10 and CIFAR-100 demonstrate the superiority of bandit-NAS over baseline NAS algorithms, such as ENAS and DQNAS, achieving lower error rates and faster search time.
This article investigates the dichotomy between higher statistical power and higher allocation to better treatment in an ethical-optimal response-adaptive design. Although many response-adaptive designs in the literat...
详细信息
This article investigates the dichotomy between higher statistical power and higher allocation to better treatment in an ethical-optimal response-adaptive design. Although many response-adaptive designs in the literature promise higher allocation to the superior treatment, this is not always guaranteed due to the variability of the designs. A new criterion for evaluating response-adaptive designs, motivated by the value-at-risk measure, is proposed to address this problem. We also provide an illustration of applying this criterion in a real clinical trial.(c) 2023 Published by Elsevier Ltd on behalf of Indian Institute of Management Bangalore. This is an open access article under the CC BY license (http://***/licenses/by/4.0/)
Twitter hosts a large and diverse amount of information that makes up a corpus of data valuable to a wide range of institutions from marketing firms to governments. Collection of tweets can enable analysis like survey...
详细信息
ISBN:
(纸本)9781665418652
Twitter hosts a large and diverse amount of information that makes up a corpus of data valuable to a wide range of institutions from marketing firms to governments. Collection of tweets can enable analysis like surveys of public opinions, marketing analysis or target analysis to users who live in a specific area. To collect useful data for a given task, the ability to capture tweets related to a specific topic sent from a specific area is needed. However, performing this kind of task on significantly sizable data sources such as the twitter stream data using just the Twitter API is a big challenge because of limitation relating to usage restrictions and lack of geotags. In this work, we propose "TLV-bandit", which collects topic-related tweets sent from a specific area based on the bandit algorithm and analyze its performance. The experimental results show that our proposed method can collect efficiently the target tweets in comparison to other methods when considering the three aspects of collection requirements: Locality (sent from the target area), Similarity (topic-related) and Volume (number of tweets).
暂无评论