Recent works have studied fair resource allocation in social settings, where fairness is judged by the impact of allocation decisions rather than more traditional minimum or maximum thresholds on the allocations themselves. Our work significantly adds to this literature by developing continuous resource allocation strategies that adhere to equality of impact, a generalization of equality of opportunity. We derive methods to maximize total welfare across groups subject to minimal violation of equality of impact, in settings where the outcomes of allocations are unknown but have a diminishing marginal effect. While focused on a two-group setting, our study addresses a broader class of welfare dynamics than explored in prior work.

Hence, a "fair" reward allocation scheme is desirable to give all parties enough incentives to join the collaboration.

Let us imagine that the grand coalition is formed by one party joining the coalition at a time. Given an order of parties (i.e., a permutationπ of N), party i joins the coalitionPiπ which denotes all parties precedingi in π. It is well-known that the Shapley value, despite its fairness, is not replication robustness in data valuation [1]. This is because the two desirable properties for fairness: symmetry and efficiency violate the replication robustness. In this work, we are interested in maintaining both the efficiency and the symmetry properties of an allocation scheme. Let us consider the case that in the grand coalitionN+, there exists a partyi+ N that is a replication of another party i N \i+ (i.e., Di = Di+).

For instance, a party with a larger contribution feels "under-rewarded"

--Reconfigurable intelligent surface (RIS) is regarded as one of the pivotal technologies for sixth-generation wireless communication systems. This paper investigates the downlink transmission of an RIS-assisted multiple-input single-output (MISO) orthogonal frequency division multiple access (OFDMA) communication systems. T o achieve a high system sum rate with low computational complexity, we develop a two-stage unsupervised learning based approach with customized loss function for the RIS reflection phase shift design, active beamforming at base station (BS) and time-frequency resource block (RB) allocation. The proposed approach consists of two neural networks: BeamNet, which takes channel state information (CSI) as input to predict the RIS reflection phase shift, and AllocationNet, which generates RB allocation decisions based on the equivalent CSI from the BS to the users, where the equivalent CSI is obtained by combining the original CSI with the RIS reflection phase shifts predicted by BeamNet. The active beamforming is implemented using the maximum ratio transmission and water-filling algorithm. In order to incorporate the discrete constraints of RIS reflection phase shift and RB allocation decisions into the network while maintaining network differentiability, we introduce a quantization function and the Gumbel softmax trick into BeamNet and AllocationNet, respectively. Furthermore, a customized loss function and phased training strategy are devised to enhance training efficiency and address quality-of-service constraints. Simulation results demonstrate that the proposed approach achieves 99.93% of the system sum rate of the successive convex approximation (SCA) method while requiring only 0.036% of its runtime. Additionally, the method's effectiveness and robustness are validated under different delay tap numbers, user distributions, and Rician factors, demonstrating its strong adaptability to different communication environments. OW ADA YS, with the large-scale deployment of fifth-generation wireless communication systems (5G), the focus of research has gradually shifted to sixth-generation wireless communication systems (6G). Y u Ma, Xingyu Zhou, Xiao Li, and Shi Jin are with the National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China (e-mail: yuma@seu.edu.cn;

--In this work, we consider the radio resource allocation problem in a wireless system with various integrated functionalities, such as communication, sensing and computing. We design suitable resource management techniques that can simultaneously cater to those heterogeneous requirements, and scale appropriately with the high-dimensional and discrete nature of the problem. We propose a novel active learning framework where resource allocation patterns are drawn sequentially, evaluated in the environment, and then used to iteratively update a surrogate model of the environment. Our method leverages a generative flow network (GFlowNet) to sample favorable solutions, as such models are trained to generate compositional objects proportionally to their training reward, hence providing an appropriate coverage of its modes. As such, GFlowNet generates diverse and high return resource management designs that update the surrogate model and swiftly discover suitable solutions. We provide simulation results showing that our method can allocate radio resources achieving 20% performance gains against benchmarks, while requiring less than half of the number of acquisition rounds.

We consider the privacy guarantees of an algorithm in which a user's data is used in $k$ steps randomly and uniformly chosen from a sequence (or set) of $t$ differentially private steps. We demonstrate that the privacy guarantees of this sampling scheme can be upper bound by the privacy guarantees of the well-studied independent (or Poisson) subsampling in which each step uses the user's data with probability $(1+ o(1))k/t $. Further, we provide two additional analysis techniques that lead to numerical improvements in some parameter regimes. The case of $k=1$ has been previously studied in the context of DP-SGD in Balle et al. (2020) and very recently in Chua et al. (2024). Privacy analysis of Balle et al. (2020) relies on privacy amplification by shuffling which leads to overly conservative bounds. Privacy analysis of Chua et al. (2024a) relies on Monte Carlo simulations that are computationally prohibitive in many practical scenarios and have additional inherent limitations.

In this paper, we investigate an accurate synchronization between a physical network and its digital network twin (DNT), which serves as a virtual representation of the physical network. The considered network includes a set of base stations (BSs) that must allocate its limited spectrum resources to serve a set of users while also transmitting its partially observed physical network information to a cloud server to generate the DNT. Since the DNT can predict the physical network status based on its historical status, the BSs may not need to send their physical network information at each time slot, allowing them to conserve spectrum resources to serve the users. However, if the DNT does not receive the physical network information of the BSs over a large time period, the DNT's accuracy in representing the physical network may degrade. To this end, each BS must decide when to send the physical network information to the cloud server to update the DNT, while also determining the spectrum resource allocation policy for both DNT synchronization and serving the users. We formulate this resource allocation task as an optimization problem, aiming to maximize the total data rate of all users while minimizing the asynchronization between the physical network and the DNT. To address this problem, we propose a method based on the GRUs and the value decomposition network (VDN). Simulation results show that our GRU and VDN based algorithm improves the weighted sum of data rates and the similarity between the status of the DNT and the physical network by up to 28.96%, compared to a baseline method combining GRU with the independent Q learning.

In recent years, reinforcement learning (RL) has gained popularity and has been applied to a wide range of tasks. One such popular domain where RL has been effective is resource management problems in systems. We look to extend work on RL for resource management problems by considering the novel domain of dynamic memory allocation management. We consider dynamic memory allocation to be a suitable domain for RL since current algorithms like first-fit, best-fit, and worst-fit can fail to adapt to changing conditions and can lead to fragmentation and suboptimal efficiency. In this paper, we present a framework in which an RL agent continuously learns from interactions with the system to improve memory management tactics. We evaluate our approach through various experiments using high-level and low-level action spaces and examine different memory allocation patterns. Our results show that RL can successfully train agents that can match and surpass traditional allocation strategies, particularly in environments characterized by adversarial request patterns. We also explore the potential of history-aware policies that leverage previous allocation requests to enhance the allocator's ability to handle complex request patterns. Overall, we find that RL offers a promising avenue for developing more adaptive and efficient memory allocation strategies, potentially overcoming limitations of hardcoded allocation algorithms.