Pub Date : 2022-06-26DOI: 10.48550/arXiv.2207.06495
E. Paolini, Lorenzo Valentini, V. Tralli, M. Chiani
An information-theoretic approach to irregular repetition slotted ALOHA (IRSA) is proposed. In contrast with previous works, in which IRSA analysis is conducted only based on quantities that are typical of collision models such as the traffic, the new approach also captures more fundamental quantities. Specifically, a suitable codebook construction for the adder channel model is adopted to establish a link with successive interference cancellation over the multi-packet reception channel. This perspective allows proving achievability and converse results for the average sum rate of IRSA multiple access schemes.
{"title":"Irregular Repetition Slotted ALOHA in an Information-Theoretic Setting","authors":"E. Paolini, Lorenzo Valentini, V. Tralli, M. Chiani","doi":"10.48550/arXiv.2207.06495","DOIUrl":"https://doi.org/10.48550/arXiv.2207.06495","url":null,"abstract":"An information-theoretic approach to irregular repetition slotted ALOHA (IRSA) is proposed. In contrast with previous works, in which IRSA analysis is conducted only based on quantities that are typical of collision models such as the traffic, the new approach also captures more fundamental quantities. Specifically, a suitable codebook construction for the adder channel model is adopted to establish a link with successive interference cancellation over the multi-packet reception channel. This perspective allows proving achievability and converse results for the average sum rate of IRSA multiple access schemes.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124003993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834818
Amit Tsvieli, N. Weinberger
The problem of learning a channel decoder for an unknown non-linear white Gaussian noise channel is considered. The learner is provided with a fixed codebook and a dataset comprised of n independent input-output samples of the channel, and is required to select a matrix for a nearest neighbor decoder with a linear kernel. The objective of maximizing the margin of the decoder is addressed. Accordingly, a regularized loss minimization problem with a codebook-related regularization term and a hinge-like loss function is developed, which is inspired by the support vector machine paradigm for classification problems. Expected generalization error bound for that hinge loss is provided for the solution of the regularized loss minimization, and shown to scale at a rate of O(1/(λn)), where λ is a regularization tradeoff parameter. In addition, a high probability uniform generalization error bound is provided for the hypothesis class, and shown to scale at a rate of $O(1/sqrt n )$. A stochastic sub-gradient descent algorithm for solving the regularized loss minimization problem is proposed, and an optimization error bound is stated, which scales at a rate of $tilde O(1/(lambda T))$. The performance of the this algorithm is demonstrated by an example.
研究了未知非线性高斯白噪声信道的信道解码器学习问题。为学习者提供一个固定的码本和一个由通道的n个独立输入输出样本组成的数据集，并要求学习者为具有线性核的最近邻解码器选择一个矩阵。解决了解码器余量最大化的目标。因此，受分类问题的支持向量机范例的启发，提出了一种具有码本相关正则化项和类铰链损失函数的正则化损失最小化问题。该铰链损失的期望泛化误差界为正则化损失最小化的解提供，并以O(1/(λn))的速率缩放，其中λ是正则化权衡参数。此外，为假设类提供了一个高概率均匀泛化误差界，并以$O(1/sqrt n )$的速率缩放。提出了一种求解正则化损失最小化问题的随机次梯度下降算法，并给出了优化误差界，其尺度为$tilde O(1/(lambda T))$。通过算例验证了该算法的性能。
{"title":"Learning Maximum Margin Channel Decoders for Non-linear Gaussian Channels","authors":"Amit Tsvieli, N. Weinberger","doi":"10.1109/ISIT50566.2022.9834818","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834818","url":null,"abstract":"The problem of learning a channel decoder for an unknown non-linear white Gaussian noise channel is considered. The learner is provided with a fixed codebook and a dataset comprised of n independent input-output samples of the channel, and is required to select a matrix for a nearest neighbor decoder with a linear kernel. The objective of maximizing the margin of the decoder is addressed. Accordingly, a regularized loss minimization problem with a codebook-related regularization term and a hinge-like loss function is developed, which is inspired by the support vector machine paradigm for classification problems. Expected generalization error bound for that hinge loss is provided for the solution of the regularized loss minimization, and shown to scale at a rate of O(1/(λn)), where λ is a regularization tradeoff parameter. In addition, a high probability uniform generalization error bound is provided for the hypothesis class, and shown to scale at a rate of $O(1/sqrt n )$. A stochastic sub-gradient descent algorithm for solving the regularized loss minimization problem is proposed, and an optimization error bound is stated, which scales at a rate of $tilde O(1/(lambda T))$. The performance of the this algorithm is demonstrated by an example.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"68 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124246161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834408
Pin-Wen Su, Yu-Chih Huang, Shih-Chun Lin, I-Hsiang Wang, Chih-Chun Wang
Channel dispersion quantifies the convergence speed of coding rate to channel capacity under different latency constraints. Under the setting of packet erasure channels (PECs) with Bernoulli packet arrivals, this work characterizes the channel dispersions of random linear streaming codes (RLSCs) and MDS block codes, respectively. New techniques are developed to quantify the channel dispersion of sequential (non-block-based) coding, the first in the literature. The channel dispersion expressions are then used to compare the levels of error protection between RLSCs and MDS block codes. The results show that if and only if the target error probability pe is smaller than a threshold (≈0.1774), RLSCs offer strictly stronger error protection than MDS block codes, which is on top of the already significant 50% latency savings of RLSCs that eliminate the queueing delay completely.
{"title":"Sequentially Mixing Randomly Arriving Packets Improves Channel Dispersion Over Block-Based Designs","authors":"Pin-Wen Su, Yu-Chih Huang, Shih-Chun Lin, I-Hsiang Wang, Chih-Chun Wang","doi":"10.1109/ISIT50566.2022.9834408","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834408","url":null,"abstract":"Channel dispersion quantifies the convergence speed of coding rate to channel capacity under different latency constraints. Under the setting of packet erasure channels (PECs) with Bernoulli packet arrivals, this work characterizes the channel dispersions of random linear streaming codes (RLSCs) and MDS block codes, respectively. New techniques are developed to quantify the channel dispersion of sequential (non-block-based) coding, the first in the literature. The channel dispersion expressions are then used to compare the levels of error protection between RLSCs and MDS block codes. The results show that if and only if the target error probability pe is smaller than a threshold (≈0.1774), RLSCs offer strictly stronger error protection than MDS block codes, which is on top of the already significant 50% latency savings of RLSCs that eliminate the queueing delay completely.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124544721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834703
Shu Hong, Lingjie Duan
In location-based services (LBSs), it is promising for multiple users to cache and share their Point-of-Interest (PoI) information with each other to reduce overall query frequency and preserve location privacy. Yet most studies on multi-user privacy preservation overlook the opportunity of leveraging service flexibility, where many users are flexible and may add obfuscation to individual LBS query. This paper is the first to study how multiple users cooperate to query with obfuscation against the adversary’s optimal inference attack, by leveraging their mutual service flexibility. Unlike the literature, even if a user already finds the shared PoI information useful, we prove it beneficial for him to further query with obfuscated location to confuse the adversary. To save the computational complexity of the max-min adversarial game problem and derive the closed-form solution, we also propose a binary approximate solution, which is proved to guarantee good privacy performance for an average user. Perhaps surprisingly, the user with greater service flexibility should choose to query the LBS with less misreported location, to maximally confuse the adversary. Finally, we numerically compare our optimal and approximate solutions with the existing approaches to show our effective privacy improvement.
{"title":"Multi-user Privacy Cooperation Game by Leveraging Users’ Service Flexibility","authors":"Shu Hong, Lingjie Duan","doi":"10.1109/ISIT50566.2022.9834703","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834703","url":null,"abstract":"In location-based services (LBSs), it is promising for multiple users to cache and share their Point-of-Interest (PoI) information with each other to reduce overall query frequency and preserve location privacy. Yet most studies on multi-user privacy preservation overlook the opportunity of leveraging service flexibility, where many users are flexible and may add obfuscation to individual LBS query. This paper is the first to study how multiple users cooperate to query with obfuscation against the adversary’s optimal inference attack, by leveraging their mutual service flexibility. Unlike the literature, even if a user already finds the shared PoI information useful, we prove it beneficial for him to further query with obfuscated location to confuse the adversary. To save the computational complexity of the max-min adversarial game problem and derive the closed-form solution, we also propose a binary approximate solution, which is proved to guarantee good privacy performance for an average user. Perhaps surprisingly, the user with greater service flexibility should choose to query the LBS with less misreported location, to maximally confuse the adversary. Finally, we numerically compare our optimal and approximate solutions with the existing approaches to show our effective privacy improvement.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122456296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834869
Hanxu Hou, Y. Han, Bo Bai, Gong Zhang
Large-scale high code-rate maximum distance separable (MDS) codes are critical and important in distributed storage systems that can provide high fault tolerance with extremely small storage redundancy. Repair access (defined as the total amount of symbols accessed in repairing one single-node failure) is a key metric of designing MDS codes. In large-scale MDS codes, one single-node failure can be recovered by connecting a large number of helper nodes. However, one or more helper nodes may be busy and can not send symbols during the repair process. In this paper, we define the total amount of symbols accessed in repairing one single-node failure with one or more busy nodes as the repair access with busy-node. We then propose a class of MDS array codes over a well-designed binary cyclic ring that is with small sub-packetization, small repair access, small repair access with busy-node, and small encoding complexity.
{"title":"Towards Efficient Repair and Coding of Binary MDS Array Codes with Small Sub-packetization","authors":"Hanxu Hou, Y. Han, Bo Bai, Gong Zhang","doi":"10.1109/ISIT50566.2022.9834869","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834869","url":null,"abstract":"Large-scale high code-rate maximum distance separable (MDS) codes are critical and important in distributed storage systems that can provide high fault tolerance with extremely small storage redundancy. Repair access (defined as the total amount of symbols accessed in repairing one single-node failure) is a key metric of designing MDS codes. In large-scale MDS codes, one single-node failure can be recovered by connecting a large number of helper nodes. However, one or more helper nodes may be busy and can not send symbols during the repair process. In this paper, we define the total amount of symbols accessed in repairing one single-node failure with one or more busy nodes as the repair access with busy-node. We then propose a class of MDS array codes over a well-designed binary cyclic ring that is with small sub-packetization, small repair access, small repair access with busy-node, and small encoding complexity.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128581984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834513
Aniruddha Phatak, M. Varanasi
Device-to-device (D2D) coded caching is considered in which there is a server hosting a library of files and a set of users. Each user is equipped with a cache memory of equal size. The system operates in two phases: first, the placement phase, in which the users’ cache memory is filled with data from the file library, followed by the delivery phase, in which each user demands one file from the library. These demands are then satisfied via user-to-user multicast transmissions only, without any involvement from the central server. For such a system, we obtain a novel lower bound on the optimal D2D sum rate. Moreover, the best known achievable D2D sum rate is shown to be within a constant multiplicative factor of 3.17 of our lower bound, improving upon the previously best known lower bound. Hence, the result in this paper further closes the gap between the best known achievable sum rate and the optimal sum rate for D2D coded caching.
{"title":"An improved lower bound for device-to-device coded caching","authors":"Aniruddha Phatak, M. Varanasi","doi":"10.1109/ISIT50566.2022.9834513","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834513","url":null,"abstract":"Device-to-device (D2D) coded caching is considered in which there is a server hosting a library of files and a set of users. Each user is equipped with a cache memory of equal size. The system operates in two phases: first, the placement phase, in which the users’ cache memory is filled with data from the file library, followed by the delivery phase, in which each user demands one file from the library. These demands are then satisfied via user-to-user multicast transmissions only, without any involvement from the central server. For such a system, we obtain a novel lower bound on the optimal D2D sum rate. Moreover, the best known achievable D2D sum rate is shown to be within a constant multiplicative factor of 3.17 of our lower bound, improving upon the previously best known lower bound. Hence, the result in this paper further closes the gap between the best known achievable sum rate and the optimal sum rate for D2D coded caching.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128612818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834697
Chih-Chun Wang
One canonical example of Age-Of-Information (AoI) minimization is the update-through-queues models. Existing results fall into two categories: The open-loop setting for which the sender is oblivious of the actual packet departure time, versus the closed-loop setting for which the decision is based on instantaneous Acknowledgement (ACK). Neither setting perfectly reflects modern networked systems, which almost always rely on feedback that experiences some delay. Motivated by this observation, this work subjects the ACK traffic to an independent queue so that the closed-loop decision is made based on delayed feedback. Near-optimal schedulers have been devised, which smoothly transition from the instantaneous-ACK to the openloop schemes depending on how long the feedback delay is. The results thus quantify the benefits of delayed feedback for AoI minimization in the update-through-queues systems.
{"title":"How Useful Is Delayed Feedback in AoI Minimization — A Study on Systems With Queues in Both Forward and Backward Directions","authors":"Chih-Chun Wang","doi":"10.1109/ISIT50566.2022.9834697","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834697","url":null,"abstract":"One canonical example of Age-Of-Information (AoI) minimization is the update-through-queues models. Existing results fall into two categories: The open-loop setting for which the sender is oblivious of the actual packet departure time, versus the closed-loop setting for which the decision is based on instantaneous Acknowledgement (ACK). Neither setting perfectly reflects modern networked systems, which almost always rely on feedback that experiences some delay. Motivated by this observation, this work subjects the ACK traffic to an independent queue so that the closed-loop decision is made based on delayed feedback. Near-optimal schedulers have been devised, which smoothly transition from the instantaneous-ACK to the openloop schemes depending on how long the feedback delay is. The results thus quantify the benefits of delayed feedback for AoI minimization in the update-through-queues systems.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129464250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834462
Tao Guo, Jie Han, Huihui Wu, Yizhu Wang, Bo Bai, Wei Han
We consider a semantic cipher system, in which we protect only the semantic information of the source. The optimal tradeoff is characterized among the coding rate, the secret key rate, the semantic information leakage rate, the source reconstruction distortion, and the semantic distortion. It is shown that an efficient key with a small size suffices to protect the semantic information.
{"title":"Protecting Semantic Information Using An Efficient Secret Key","authors":"Tao Guo, Jie Han, Huihui Wu, Yizhu Wang, Bo Bai, Wei Han","doi":"10.1109/ISIT50566.2022.9834462","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834462","url":null,"abstract":"We consider a semantic cipher system, in which we protect only the semantic information of the source. The optimal tradeoff is characterized among the coding rate, the secret key rate, the semantic information leakage rate, the source reconstruction distortion, and the semantic distortion. It is shown that an efficient key with a small size suffices to protect the semantic information.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130556187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834492
Bo Wu, Jincheng Dai, K. Niu
In this paper, we investigate the joint design and optimization of source-channel polar coding with 2m-ary transmission. A joint framework is proposed which includes a source polar code to compress the redundant source, followed by a set of component polar codes over a 2m-ary modulation to protect the source against errors and achieve increased spectral efficiency. We prove that our scheme suffices to achieve the theoretical limit of source-channel separation theorem. For finite-length cases, a joint decoder that exploits both the residual redundancy and channel characteristics is also derived to further reduce the error rate. Simulation results verify the effectiveness of the scheme.
{"title":"Joint Source-Channel Polar-Coded Modulation","authors":"Bo Wu, Jincheng Dai, K. Niu","doi":"10.1109/ISIT50566.2022.9834492","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834492","url":null,"abstract":"In this paper, we investigate the joint design and optimization of source-channel polar coding with 2m-ary transmission. A joint framework is proposed which includes a source polar code to compress the redundant source, followed by a set of component polar codes over a 2m-ary modulation to protect the source against errors and achieve increased spectral efficiency. We prove that our scheme suffices to achieve the theoretical limit of source-channel separation theorem. For finite-length cases, a joint decoder that exploits both the residual redundancy and channel characteristics is also derived to further reduce the error rate. Simulation results verify the effectiveness of the scheme.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130656895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-26DOI: 10.1109/ISIT50566.2022.9834746
N. Weinberger, M. Yemini
We introduce a multi-armed bandit problem with information-based rewards. At each round, a player chooses an arm, observes a symbol, and receives an unobserved reward in the form of the symbol’s self-information. The player aims to maximize the expected total reward associated with the entropy values of the arms played. We propose two algorithms based on upper confidence bounds (UCB) for this model. The first algorithm optimistically corrects the bias term in the entropy estimation. The second algorithm relies on data-dependent UCBs that adapt to sources with small entropy values. We provide performance guarantees by upper bounding the expected regret of each of the algorithms, and compare their asymptotic behavior to the Lai-Robbins lower bound. Finally, we provide numerical results illustrating the regret of the algorithms presented.
{"title":"Upper Confidence Interval Strategies for Multi-Armed Bandits with Entropy Rewards","authors":"N. Weinberger, M. Yemini","doi":"10.1109/ISIT50566.2022.9834746","DOIUrl":"https://doi.org/10.1109/ISIT50566.2022.9834746","url":null,"abstract":"We introduce a multi-armed bandit problem with information-based rewards. At each round, a player chooses an arm, observes a symbol, and receives an unobserved reward in the form of the symbol’s self-information. The player aims to maximize the expected total reward associated with the entropy values of the arms played. We propose two algorithms based on upper confidence bounds (UCB) for this model. The first algorithm optimistically corrects the bias term in the entropy estimation. The second algorithm relies on data-dependent UCBs that adapt to sources with small entropy values. We provide performance guarantees by upper bounding the expected regret of each of the algorithms, and compare their asymptotic behavior to the Lai-Robbins lower bound. Finally, we provide numerical results illustrating the regret of the algorithms presented.","PeriodicalId":348168,"journal":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129536420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：