Differential privacy (DP) provides robust privacy guarantees for statistical inference, but this can lead to unreliable results and biases in downstream applications. While several noise-aware approaches have been proposed which integrate DP perturbation into the inference, they are limited to specific types of simple probabilistic models. In this work, we propose a novel method for noise-aware approximate Bayesian inference based on stochastic gradient variational inference which can also be applied to high-dimensional and non-conjugate models. We also propose a more accurate evaluation method for noise-aware posteriors. Empirically, our inference method has similar performance to existing methods in the domain where they are applicable. Outside this domain, we obtain accurate coverages on high-dimensional Bayesian linear regression and well-calibrated predictive probabilities on Bayesian logistic regression with the UCI Adult dataset.

Autonomous agents require the capability to identify dynamic objects in their environment for safe planning and navigation. Incomplete and erroneous dynamic detections jeopardize the agent's ability to accomplish its task. Dynamic detection is a challenging problem due to the numerous sources of uncertainty inherent in the problem's inputs and the wide variety of applications, which often lead to use-case-tailored solutions. We propose a robust learning-free approach to segment moving objects in point cloud data. The foundation of the approach lies in modelling each voxel using a hidden Markov model (HMM), and probabilistically integrating beliefs into a map using an HMM filter. The proposed approach is tested on benchmark datasets and consistently performs better than or as well as state-of-the-art methods with strong generalized performance across sensor characteristics and environments. The approach is open-sourced at https://github.com/vb44/HMM-MOS.

Probabilistic circuits (PCs) have emerged as a powerful framework to compactly represent probability distributions for efficient and exact probabilistic inference. It has been shown that PCs with a general directed acyclic graph (DAG) structure can be understood as a mixture of exponentially (in its height) many components, each of which is a product distribution over univariate marginals. However, existing structure learning algorithms for PCs often generate tree-structured circuits or use tree-structured circuits as intermediate steps to compress them into DAG-structured circuits. This leads to the intriguing question of whether there exists an exponential gap between DAGs and trees for the PC structure. In this paper, we provide a negative answer to this conjecture by proving that, for $n$ variables, there exists a quasi-polynomial upper bound $n^{O(\log n)}$ on the size of an equivalent tree computing the same probability distribution. On the other hand, we also show that given a depth restriction on the tree, there is a super-polynomial separation between tree and DAG-structured PCs. Our work takes an important step towards understanding the expressive power of tree-structured PCs, and our techniques may be of independent interest in the study of structure learning algorithms for PCs.

Beam tracking is an essential functionality of millimeter wave (mmWave, 30-100 GHz) and sub-terahertz (sub-THz, 100-300 GHz) 5G/6G systems. It operates by performing antenna sweeping at both base station (BS) and user equipment (UE) sides using the Synchronization Signal Blocks (SSB). The optimal frequency of beam tracking events is not specified by 3GPP standards and heavily depends on the micromobility properties of the applications currently utilized by the user. In absence of explicit signalling for the type of application at the air interface, in this paper, we propose a way to remotely detect it at the BS side based on the received signal strength pattern. To this aim, we first perform a multi-stage measurement campaign at 156 GHz, belonging to the sub-THz band, to obtain the received signal strength traces of popular smartphone applications. Then, we proceed applying conventional statistical Mann-Whitney tests and various machine learning (ML) based classification techniques to discriminate applications remotely. Our results show that Mann-Whitney test can be used to differentiate between fast and slow application classes with a confidence of 0.95 inducing class detection delay on the order of 1 s after application initialization. With the same time budget, random forest classifiers can differentiate between applications with fast and slow micromobility with 80% accuracy using received signal strength metric only. The accuracy of detecting a specific application however is lower, reaching 60%. By utilizing the proposed technique one can estimate the optimal values of the beam tracking intervals without adding additional signalling to the air interface.

Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation among self-interested, independent learning agents? Promising recent work has shown that in certain tasks cooperation can be established between learning-aware agents who model the learning dynamics of each other. Here, we present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning, which takes into account that other agents are themselves learning through trial and error based on multiple noisy trials. We then leverage efficient sequence models to condition behavior on long observation histories that contain traces of the learning dynamics of other agents. Training long-context policies with our algorithm leads to cooperative behavior and high returns on standard social dilemmas, including a challenging environment where temporally-extended action coordination is required. Finally, we derive from the iterated prisoner's dilemma a novel explanation for how and when cooperation arises among self-interested learning-aware agents.

In neuroscience, researchers typically conduct experiments under multiple conditions to acquire neural responses in the form of high-dimensional spike train datasets. Analysing high-dimensional spike data is a challenging statistical problem. To this end, Gaussian process factor analysis (GPFA), a popular class of latent variable models has been proposed. GPFA extracts smooth, low-dimensional latent trajectories underlying high-dimensional spike train datasets. However, such analyses are often done separately for each experimental condition, contrary to the nature of neural datasets, which contain recordings under multiple experimental conditions. Exploiting the parametric nature of these conditions, we propose a multi-condition GPFA model and inference procedure to learn the underlying latent structure in the corresponding datasets in sample-efficient manner. In particular, we propose a non-parametric Bayesian approach to learn a smooth tuning function over the experiment condition space. Our approach not only boosts model accuracy and is faster, but also improves model interpretability compared to approaches that separately fit models for each experimental condition.

Recent advances in multi-agent reinforcement learning (MARL) have created opportunities to solve complex real-world tasks. Cybersecurity is a notable application area, where defending networks against sophisticated adversaries remains a challenging task typically performed by teams of security operators. In this work, we explore novel MARL strategies for building autonomous cyber network defenses that address challenges such as large policy spaces, partial observability, and stealthy, deceptive adversarial strategies. To facilitate efficient and generalized learning, we propose a hierarchical Proximal Policy Optimization (PPO) architecture that decomposes the cyber defense task into specific sub-tasks like network investigation and host recovery. Our approach involves training sub-policies for each sub-task using PPO enhanced with domain expertise. These sub-policies are then leveraged by a master defense policy that coordinates their selection to solve complex network defense tasks. Furthermore, the sub-policies can be fine-tuned and transferred with minimal cost to defend against shifts in adversarial behavior or changes in network settings. We conduct extensive experiments using CybORG Cage 4, the state-of-the-art MARL environment for cyber defense. Comparisons with multiple baselines across different adversaries show that our hierarchical learning approach achieves top performance in terms of convergence speed, episodic return, and several interpretable metrics relevant to cybersecurity, including the fraction of clean machines on the network, precision, and false positives on recoveries.

Inventory control in modern supply chains has attracted significant attention due to the increasing number of disruptive shocks and the challenges posed by complex dynamics, uncertainties, and limited collaboration. Traditional methods, which often rely on static parameters, struggle to adapt to changing environments. This paper proposes a Multi-Agent Reinforcement Learning (MARL) framework with Graph Neural Networks (GNNs) for state representation to address these limitations. Our approach redefines the action space by parameterizing heuristic inventory control policies, making it adaptive as the parameters dynamically adjust based on system conditions. By leveraging the inherent graph structure of supply chains, our framework enables agents to learn the system's topology, and we employ a centralized learning, decentralized execution scheme that allows agents to learn collaboratively while overcoming information-sharing constraints. Additionally, we incorporate global mean pooling and regularization techniques to enhance performance. We test the capabilities of our proposed approach on four different supply chain configurations and conduct a sensitivity analysis. This work paves the way for utilizing MARL-GNN frameworks to improve inventory management in complex, decentralized supply chain environments.

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover diverse states. However, in complex environments with many state factors (e.g., household environments with many objects), learning skills that cover all possible states is impossible, and naively encouraging state diversity often leads to simple skills that are not ideal for solving downstream tasks. This work introduces Skill Discovery from Local Dependencies (Skild), which leverages state factorization as a natural inductive bias to guide the skill learning process. The key intuition guiding Skild is that skills that induce diverse interactions between state factors are often more valuable for solving downstream tasks. To this end, Skild develops a novel skill learning objective that explicitly encourages the mastering of skills that effectively induce different interactions within an environment. We evaluate Skild in several domains with challenging, long-horizon sparse reward tasks including a realistic simulated household robot domain, where Skild successfully learns skills with clear semantic meaning and shows superior performance compared to existing unsupervised reinforcement learning methods that only maximize state coverage.

A Bayesian coreset is a small, weighted subset of a data set that replaces the full data during inference to reduce computational cost. The state-of-the-art coreset construction algorithm, Coreset Markov chain Monte Carlo (Coreset MCMC), uses draws from an adaptive Markov chain targeting the coreset posterior to train the coreset weights via stochastic gradient optimization. However, the quality of the constructed coreset, and thus the quality of its posterior approximation, is sensitive to the stochastic optimization learning rate. In this work, we propose a learning-rate-free stochastic gradient optimization procedure, Hot-start Distance over Gradient (Hot DoG), Figure 1: Relative Coreset MCMC posterior approximation for training coreset weights in Coreset MCMC error (average squared coordinate-wise z-score) without user tuning effort. Empirical results using ADAM with different learning rates versus the demonstrate that Hot DoG provides higher proposed Hot DoG method (with fixed r = 0.001). Median quality posterior approximations than other values after 200,000 optimization iterations across learning-rate-free stochastic gradient methods, 10 trials are used for the relative comparison for a variety and performs competitively to optimallytuned of datasets, models, and coreset sizes.