Reinforcement learning (RL) gained considerable attention by creating decision-making agents that maximize rewards received from fully observable environments. However, many real-world problems are partially or noisily observable by nature, where agents do not receive the true and complete state of the environment. Such problems are formulated as partially observable Markov decision processes (POMDPs). Some studies applied RL to POMDPs by recalling previous decisions and observations or inferring the true state of the environment from received observations. Nevertheless, aggregating observations and decisions over time is impractical for environments with high-dimensional continuous state and action spaces. Moreover, so-called inference-based RL approaches require large number of samples to perform well since agents eschew uncertainty in the inferred state for the decision-making. Active inference is a framework that is naturally formulated in POMDPs and directs agents to select decisions by minimising expected free energy (EFE). This supplies reward-maximising (exploitative) behaviour in RL, with an information-seeking (exploratory) behaviour. Despite this exploratory behaviour of active inference, its usage is limited to discrete state and action spaces due to the computational difficulty of the EFE. We propose a unified principle for joint information-seeking and reward maximization that clarifies a theoretical connection between active inference and RL, unifies active inference and RL, and overcomes their aforementioned limitations. Our findings are supported by strong theoretical analysis. The proposed framework's superior exploration property is also validated by experimental results on partial observable tasks with high-dimensional continuous state and action spaces. Moreover, the results show that our model solves reward-free problems, making task reward design optional.

分布式多智能经纪增强学习（Marl）算法最近引起了兴趣激增，主要是由于深神经网络（DNN）的最新进步。由于利用固定奖励模型来学习基础值函数，传统的基于模型（MB）或无模型（MF）RL算法不可直接适用于MARL问题。虽然涉及单一代理时，基于DNN的解决方案完全良好地表现出，但是这种方法无法完全推广到MARL问题的复杂性。换句话说，尽管最近的基于DNN的DNN用于多种子体环境的方法取得了卓越的性能，但它们仍然容易出现过度，对参数选择的高敏感性，以及样本低效率。本文提出了多代理自适应Kalman时间差（MAK-TD）框架及其继任者表示的基于代表的变体，称为MAK-SR。直观地说，主要目标是利用卡尔曼滤波（KF）的独特特征，如不确定性建模和在线二阶学习。提议的MAK-TD / SR框架考虑了与高维多算法环境相关联的动作空间的连续性，并利用卡尔曼时间差（KTD）来解决参数不确定性。通过利用KTD框架，SR学习过程被建模到过滤问题，其中径向基函数（RBF）估计器用于将连续空间编码为特征向量。另一方面，对于学习本地化奖励功能，我们求助于多种模型自适应估计（MMAE），处理缺乏关于观察噪声协方差和观察映射功能的先前知识。拟议的MAK-TD / SR框架通过多个实验进行评估，该实验通过Openai Gym Marl基准实施。

Privacy-preserving inference via edge or encrypted computing paradigms encourages users of machine learning services to confidentially run a model on their personal data for a target task and only share the model's outputs with the service provider; e.g., to activate further services. Nevertheless, despite all confidentiality efforts, we show that a ''vicious'' service provider can approximately reconstruct its users' personal data by observing only the model's outputs, while keeping the target utility of the model very close to that of a ''honest'' service provider. We show the possibility of jointly training a target model (to be run at users' side) and an attack model for data reconstruction (to be secretly used at server's side). We introduce the ''reconstruction risk'': a new measure for assessing the quality of reconstructed data that better captures the privacy risk of such attacks. Experimental results on 6 benchmark datasets show that for low-complexity data types, or for tasks with larger number of classes, a user's personal data can be approximately reconstructed from the outputs of a single target inference task. We propose a potential defense mechanism that helps to distinguish vicious vs. honest classifiers at inference time. We conclude this paper by discussing current challenges and open directions for future studies. We open-source our code and results, as a benchmark for future work.

Federated learning (FL) on deep neural networks facilitates new applications at the edge, especially for wearable and Internet-of-Thing devices. Such devices capture a large and diverse amount of data, but they have memory, compute, power, and connectivity constraints which hinder their participation in FL. We propose Centaur, a multitier FL framework, enabling ultra-constrained devices to efficiently participate in FL on large neural nets. Centaur combines two major ideas: (i) a data selection scheme to choose a portion of samples that accelerates the learning, and (ii) a partition-based training algorithm that integrates both constrained and powerful devices owned by the same user. Evaluations, on four benchmark neural nets and three datasets, show that Centaur gains ~10% higher accuracy than local training on constrained devices with ~58% energy saving on average. Our experimental results also demonstrate the superior efficiency of Centaur when dealing with imbalanced data, client participation heterogeneity, and various network connection probabilities.

Bilevel programming has recently received attention in the literature, due to a wide range of applications, including reinforcement learning and hyper-parameter optimization. However, it is widely assumed that the underlying bilevel optimization problem is solved either by a single machine or in the case of multiple machines connected in a star-shaped network, i.e., federated learning setting. The latter approach suffers from a high communication cost on the central node (e.g., parameter server) and exhibits privacy vulnerabilities. Hence, it is of interest to develop methods that solve bilevel optimization problems in a communication-efficient decentralized manner. To that end, this paper introduces a penalty function based decentralized algorithm with theoretical guarantees for this class of optimization problems. Specifically, a distributed alternating gradient-type algorithm for solving consensus bilevel programming over a decentralized network is developed. A key feature of the proposed algorithm is to estimate the hyper-gradient of the penalty function via decentralized computation of matrix-vector products and few vector communications, which is then integrated within our alternating algorithm to give the finite-time convergence analysis under different convexity assumptions. Owing to the generality of this complexity analysis, our result yields convergence rates for a wide variety of consensus problems including minimax and compositional optimization. Empirical results on both synthetic and real datasets demonstrate that the proposed method works well in practice.

自适应梯度算法（例如Adagrad及其变体）在培训深神经网络方面已广受欢迎。尽管许多适合自适应方法的工作都集中在静态的遗憾上，作为实现良好遗憾保证的性能指标，但对这些方法的动态遗憾分析尚不清楚。与静态的遗憾相反，动态遗憾被认为是绩效测量的更强大的概念，因为它明确阐明了环境的非平稳性。在本文中，我们通过动态遗憾的概念在一个强大的凸面设置中浏览了Adagrad（称为M-Adagrad）的一种变体，该遗憾衡量了在线学习者的性能，而不是参考（最佳）解决方案，这可能会改变时间。我们证明了根据最小化序列的路径长度的束缚，该序列基本上反映了环境的非平稳性。此外，我们通过利用每个回合中学习者的多个访问权限来增强动态遗憾。经验结果表明，M-Adagrad在实践中也很好。

动机：在超声引导活检过程中检测前列腺癌是具有挑战性的。癌症的高度异质外观，超声伪像的存在和噪声都导致了这些困难。高频超声成像的最新进展 - 微拆卸 - 在高分辨率下大大提高了组织成像的能力。我们的目的是研究专门针对微型启动引导的前列腺癌活检的强大深度学习模型的发展。对于临床采用的模型，一个关键的挑战是设计一种可以确定癌症的解决方案，同时从粗略的组织病理学测量中学习引入弱标签的活检样品。方法：我们使用了从194例接受了前列腺活检的患者中获得的微型图像的数据集。我们使用共同教学范式来训练一个深层模型，以处理标签中的噪声，以及一种证据深度学习方法进行不确定性估计。我们使用准确性与信心的临床相关指标评估了模型的性能。结果：我们的模型实现了对预测不确定性的良好估计，而面积为88 $ \％$。联合结合中的共同教学和证据深度学习的使用比单独单独的不确定性估计明显更好。在不确定性估计中，我们还提供了与最先进的比较。

对协作学习的实证攻击表明，深度神经网络的梯度不仅可以披露训练数据的私有潜在属性，还可以用于重建原始数据。虽然先前的作品试图量化了梯度的隐私风险，但这些措施没有建立理论上对梯度泄漏的理解了解，而不是跨越攻击者的概括，并且不能完全解释通过实际攻击在实践中通过实证攻击观察到的内容。在本文中，我们介绍了理论上激励的措施，以量化攻击依赖和攻击无关方式的信息泄漏。具体而言，我们展示了$ \ mathcal {v} $ - 信息的适应，它概括了经验攻击成功率，并允许量化可以从任何所选择的攻击模型系列泄漏的信息量。然后，我们提出了独立的措施，只需要共享梯度，用于量化原始和潜在信息泄漏。我们的经验结果，六个数据集和四种流行型号，揭示了第一层的梯度包含最高量的原始信息，而（卷积）特征提取器层之后的（完全连接的）分类层包含最高的潜在信息。此外，我们展示了如何在训练期间诸如梯度聚集的技术如何减轻信息泄漏。我们的工作为更好的防御方式铺平了道路，例如基于层的保护或强聚合。