This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violati...
详细信息
This paper presents a cardiac MRI image segmentation model based on an improved U-Net architecture. Accurate segmentation of cardiac MRI images is critical for the diagnosis and treatment of cardiovascular diseases, y...
详细信息
ISBN:
(数字)9798350355413
ISBN:
(纸本)9798350355420
This paper presents a cardiac MRI image segmentation model based on an improved U-Net architecture. Accurate segmentation of cardiac MRI images is critical for the diagnosis and treatment of cardiovascular diseases, yet existing U-Net models exhibit limitations in handling complex cardiac structures and multi-scale features. To address these challenges, this paper proposes two key enhancements. First, we propose a Multi-Dimensional Context Attention module, designed to improve the integration of global and local information within the skip connections, thereby enhancing segmentation accuracy for intricate cardiac structures. Furthermore, we propose a Reverse Feature Modulation module, which generates reverse masks and dynamically adjusts feature weights across different classes using adaptive weighting, effectively mitigating class imbalance issues in multi-class segmentation tasks and improving focus on difficult-to-segment regions. Experimental results demonstrate that the proposed model outperforms the standard U-Net on the ACDC dataset, achieving significant improvements in evaluation metrics such as the Dice coefficient. These enhancements underscore the model's efficacy and robustness in complex cardiac image segmentation tasks, offering new technical support for automated cardiovascular disease diagnosis.
This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violati...
详细信息
In this paper we deal with stochastic optimization problems where the data distributions change in response to the decision variables. Traditionally, the study of optimization problems with decision-dependent distribu...
详细信息
This paper considers distributed nonconvex op-timization for minimizing the average of local cost functions, by using local information exchange over undirected communication networks. Since the communication channels...
详细信息
ISBN:
(数字)9781665467612
ISBN:
(纸本)9781665467629
This paper considers distributed nonconvex op-timization for minimizing the average of local cost functions, by using local information exchange over undirected communication networks. Since the communication channels often have limited bandwidth or capacity, we first introduce a quantization rule and an encoder/decoder scheme to reduce the transmission bits. By integrating them with a distributed algorithm, we then propose a distributed quantized nonconvex optimization algorithm. Assuming the global cost function satisfies the Polyak– Łojasiewicz condition, which does not require the global cost function to be convex and the global minimizer is not necessarily unique, we show that the proposed algorithm linearly converges to a global optimal point. Moreover, a low data rate is shown to be sufficient to ensure linear convergence when the algorithm parameters are properly chosen. The theoretical results are illustrated by numerical simulation examples.
This paper considers distributed online convex optimization with adversarial constraints. In this setting, a network of agents makes decisions at each round, and then only a portion of the loss function and a coordina...
详细信息
In this paper, we study the distributed nonconvex optimization problem, aiming to minimize the average value of the local nonconvex cost functions using local information exchange. To reduce the communication overhead...
详细信息
Radio frequency identification technology (RFID) is currently widely used in different applications such as inventory management, tracking or monitoring because of its high identification quality and low-cost. However...
详细信息
This paper considers distributed online nonconvex optimization with time-varying inequality constraints over a network of agents. For a time-varying graph, we propose a distributed online primal–dual algorithm with c...
详细信息
This paper considers distributed online nonconvex optimization with time-varying inequality constraints over a network of agents, where the nonconvex local loss and convex local constraint functions can vary arbitrari...
详细信息
This paper considers distributed online nonconvex optimization with time-varying inequality constraints over a network of agents, where the nonconvex local loss and convex local constraint functions can vary arbitrarily across iterations, and the information of them is privately revealed to each agent at each iteration. For a uniformly jointly strongly connected time-varying directed graph, we propose two distributed bandit online primal–dual algorithm with compressed communication to efficiently utilize communication resources in the one-point and two-point bandit feedback settings, respectively. In nonconvex optimization, finding a globally optimal decision is often NP-hard. As a result, the standard regret metric used in online convex optimization becomes inapplicable. To measure the performance of the proposed algorithms, we use a network regret metric grounded in the first-order optimality condition associated with the variational inequality. We show that the compressed algorithm with one-point bandit feedback establishes an O(Tθ1) network regret bound and an O(T7/4−θ1) network cumulative constraint violation bound, where T is the number of iterations and θ1 ∈ (3/4,5/6] is a user-defined trade-off parameter. When Slater’s condition holds (i.e, there is a point that strictly satisfies the inequality constraints at all iterations), the network cumulative constraint violation bound is reduced to O(T5/2−2θ1). In addition, we show that the compressed algorithm with two-point bandit feedback establishes an O(Tmax{1−θ1,θ1}) network regret and an O(T1−θ1/2) network cumulative constraint violation bounds, where θ1 ∈ (0,1). Moreover, the network cumulative constraint violation bound is reduced to O(T1−θ1) under Slater’s condition. The bounds are comparable to the state-of-the-art results established by existing distributed online algorithms with perfect communication for distributed online convex optimization with inequality constraints. To the best of our knowledge, thi
暂无评论