Alternating direction method of multiplier (ADMM) is a powerful method to solve decentralized convex optimization problems. In distributed settings, each node performs computation with its local data and the local results are exchanged among neighboring nodes in an iterative fashion. During this iterative process the leakage of data privacy arises and can accumulate significantly over many iterations, making it difficult to balance the privacy-accuracy tradeoff. We propose Recycled ADMM (R-ADMM), where a linear approximation is applied to every even iteration, its solution directly calculated using only results from the previous, odd iteration. It turns out that under such a scheme, half of the updates incur no privacy loss and require much less computation compared to the conventional ADMM. Moreover, R-ADMM can be further modified (MR-ADMM) such that each node independently determines its own penalty parameter over iterations. We obtain a sufficient condition for the convergence of both algorithms and provide the privacy analysis based on objective perturbation. It can be shown that the privacy-accuracy tradeoff can be improved significantly compared with conventional ADMM.

We consider the provision of public goods on networks of strategic agents. We study different effort outcomes of these network games, namely, the Nash equilibria, Pareto efficient effort profiles, and semi-cooperative equilibria (resulting from interactions among coalitions of agents). We identify necessary and sufficient conditions on the structure of the network for the uniqueness of the Nash equilibrium by using a connection between these outcomes and linear complementarity problems. We show that our finding unifies, and extends, existing results in the literature. We also identify conditions for the existence of Nash equilibria for two subclasses of games at the two extremes of our model, namely games of strategic complements and games of strategic substitutes. We provide a graph-theoretical interpretation of agents' efforts at the Nash equilibrium, as well as the Pareto efficient outcomes and semi-cooperative equilibria, by linking an agent's decision to her centrality in the interaction network. Using this connection, we separate the effects of incoming and outgoing edges on agents' efforts and uncover an alternating effect over walks of different length in the network.

In this paper we propose the use of large language models (LLMs) for characterizing, clustering, and fingerprinting raw text obtained from network measurements. To this end, We first train a transformer-based masked language model, namely RoBERTa, on a dataset containing hundreds of millions of banners obtained from Internet-wide scans. We further fine-tune this model using a contrastive loss function (driven by domain knowledge) to produce temporally stable numerical representations (embeddings) that can be used out-of-the-box for downstream learning tasks. Our embeddings are robust, resilient to small random changes in the content of a banner, and maintain proximity between embeddings of similar hardware/software products. We further cluster HTTP banners using a density-based approach (HDBSCAN), and examine the obtained clusters to generate text-based fingerprints for the purpose of labeling raw scan data. We compare our fingerprints to Recog, an existing database of manually curated fingerprints, and show that we can identify new IoT devices and server products that were not previously captured by Recog. Our proposed methodology poses an important direction for future research by utilizing state-of-the-art language models to automatically analyze, interpret, and label the large amounts of data generated by Internet scans.

Machine learning models developed from real-world data can inherit potential, preexisting bias in the dataset. When these models are used to inform decisions involving human beings, fairness concerns inevitably arise. Imposing certain fairness constraints in the training of models can be effective only if appropriate criteria are applied. However, a fairness criterion can be defined/assessed only when the interaction between the decisions and the underlying population is well understood. We introduce two feedback models describing how people react when receiving machine-aided decisions and illustrate that some commonly used fairness criteria can end with undesirable consequences while reinforcing discrimination.

In this monograph we provide a tutorial on a family of sequential learning and decision problems known as the multi-armed bandit problems. We introduce a wide range of application scenarios for this learning framework, as well as its many different variants. The more detailed discussion is focused on the stochastic bandit problems, with rewards driven by either an IID or a Markov process, and when the environment consists of a single or multiple simultaneous users. We also present literature on the learning of MDPs, which captures coupling among the evolution of different options that a classical MAB problem does not.