George Pappas

Matthew Cleaveland, Lars Lindemann, Radoslav Ivanov et al.

Motivated by the fragility of neural network (NN) controllers in safety-critical applications, we present a data-driven framework for verifying the risk of stochastic dynamical systems with NN controllers. Given a stochastic control system, an NN controller, and a specification equipped with a notion of trace robustness (e.g., constraint functions or signal temporal logic), we collect trajectories from the system that may or may not satisfy the specification. In particular, each of the trajectories produces a robustness value that indicates how well (severely) the specification is satisfied (violated). We then compute risk metrics over these robustness values to estimate the risk that the NN controller will not satisfy the specification. We are further interested in quantifying the difference in risk between two systems, and we show how the risk estimated from a nominal system can provide an upper bound the risk of a perturbed version of the system. In particular, the tightness of this bound depends on the closeness of the systems in terms of the closeness of their system trajectories. For Lipschitz continuous and incrementally input-to-state stable systems, we show how to exactly quantify system closeness with varying degrees of conservatism, while we estimate system closeness for more general systems from data in our experiments. We demonstrate our risk verification approach on two case studies, an underwater vehicle and an F1/10 autonomous car.

Haoze Wu, Teruhiro Tagomori, Alexander Robey et al.

We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts. To do so, we bridge the gap between hand-crafted specifications and realistic deployment settings by proposing a novel neural-symbolic verification framework, in which we train a generative model to learn perturbations from data and define specifications with respect to the output of the learned model. A unique challenge arising from this setting is that existing verifiers cannot tightly approximate sigmoid activations, which are fundamental to many state-of-the-art generative models. To address this challenge, we propose a general meta-algorithm for handling sigmoid activations which leverages classical notions of counter-example-guided abstraction refinement. The key idea is to "lazily" refine the abstraction of sigmoid functions to exclude spurious counter-examples found in the previous abstraction, thus guaranteeing progress in the verification process while keeping the state-space small. Experiments on the MNIST and CIFAR-10 datasets show that our framework significantly outperforms existing methods on a range of challenging distribution shifts.

Victor M. Preciado, Michael Zargham, Chinwendu Enyioha et al.

In this chapter, we consider the problem of designing protection strategies to contain spreading processes in complex cyber-physical networks. We illustrate our ideas using a family of bio-motivated spreading models originally proposed in the epidemiological literature, e.g., the Susceptible-Infected-Susceptible (SIS) model. We first introduce a framework in which we are allowed to distribute two types of resources in order to contain the spread, namely, (i) preventive resources able to reduce the spreading rate, and (ii) corrective resources able to increase the recovery rate of nodes in which the resources are allocated. In practice, these resources have an associated cost that depends on either the resiliency level achieved by the preventive resource, or the restoration efficiency of the corrective resource. We present a mathematical framework, based on dynamic systems theory and convex optimization, to find the cost-optimal distribution of protection resources in a network to contain the spread. We also present two extensions to this framework in which (i) we consider generalized epidemic models, beyond the simple SIS model, and (ii) we assume uncertainties in the contact network in which the spreading is taking place. We compare these protection strategies with common heuristics previously proposed in the literature and illustrate our results with numerical simulations using the air traffic network.

David Snyder, Apurva Badithela, Nikolai Matni et al.

Generalist robot manipulation policies are becoming increasingly capable, but are limited in evaluation to a small number of hardware rollouts. This strong resource constraint in real-world testing necessitates both more informative performance measures and reliable and efficient evaluation procedures to properly assess model capabilities and benchmark progress in the field. This work presents a novel framework for robot policy comparison that is sample-efficient, statistically rigorous, and applicable to a broad set of evaluation metrics used in practice. Based on safe, anytime-valid inference (SAVI), our test procedure is sequential, allowing the evaluator to stop early when sufficient statistical evidence has accumulated to reach a decision at a pre-specified level of confidence. Unlike previous work developed for binary success, our unified approach addresses a wide range of informative metrics: from discrete partial credit task progress to continuous measures of episodic reward or trajectory smoothness, spanning both parametric and nonparametric comparison problems. Through extensive validation on simulated and real-world evaluation data, we demonstrate up to 70% reduction in evaluation burden compared to standard batch methods and up to 50% reduction compared to state-of-the-art sequential procedures designed for binary outcomes, with no loss of statistical rigor. Notably, our empirical results show that competing policies can be separated more quickly when using fine-grained task progress than binary success metrics.

Nikolaos Bousias, Charalampia Stamouli, Anastasios Tsiamis et al.

Control barrier functions (CBFs) provide a powerful tool for enforcing safety constraints in control systems, but their direct application to complex, high-dimensional dynamics is often challenging. In many settings, safety certificates are more naturally designed for simplified or alternative system models that do not exactly match the dynamics of interest. This paper addresses the problem of transferring safety guarantees between dynamical systems with mismatched dynamics. We propose a transferred control barrier function (tCBF) framework that enables safety constraints defined on one system to be systematically enforced on another system using a simulation function and an explicit margin term. The resulting transferred barrier accounts for model mismatch and induces a safety condition that can be enforced on the target system via a quadratic-program-based safety filter. The proposed approach is general and does not require the two systems to share the same state dimension or dynamics. We demonstrate the effectiveness of the framework on a quadrotor navigation task with the transferred barrier ensuring collision avoidance for the target system, while remaining minimally invasive to a nominal controller. These results highlight the potential of transferred control barrier functions as a general mechanism for enforcing safety across heterogeneous dynamical systems.

Sima Noorani, Shayan Kiyani, Hamed Hassani et al.

As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles: counterfactual harm, ensuring the AI does not undermine human strengths, and complementarity, ensuring it adds value where the human is prone to err. We formalize these concepts via user defined rules, allowing users to specify exactly what harm and complementarity mean for their specific task. We then introduce an online, distribution free algorithm with finite sample guarantees that enforces the user-specified constraints over the collaboration dynamics. We evaluate our framework across two interactive settings: LLM simulated collaboration on a medical diagnostic task and a human crowdsourcing study on a pictorial reasoning task. We show that our online procedure maintains prescribed counterfactual harm and complementarity violation rates even under nonstationary interaction dynamics. Moreover, tightening or loosening these constraints produces predictable shifts in downstream human accuracy, confirming that the two principles serve as practical levers for steering multi-round collaboration toward better decision quality without the need to model or constrain human behavior.

Shayan Kiyani, Sima Noorani, George Pappas et al.

Reasoning with LLMs increasingly unfolds inside a broader verification loop. Internally, systems use cheap checks, such as self-consistency or proxy rewards, which we call weak verification. Externally, users inspect outputs and steer the model through feedback until results are trustworthy, which we call strong verification. These signals differ sharply in cost and reliability: strong verification can establish trust but is resource-intensive, while weak verification is fast and scalable but noisy and imperfect. We formalize this tension through weak--strong verification policies, which decide when to accept or reject based on weak verification and when to defer to strong verification. We introduce metrics capturing incorrect acceptance, incorrect rejection, and strong-verification frequency. Over population, we show that optimal policies admit a two-threshold structure and that calibration and sharpness govern the value of weak verifiers. Building on this, we develop an online algorithm that provably controls acceptance and rejection errors without assumptions on the query stream, the language model, or the weak verifier.

Mahdi Sabbaghi, George Pappas, Adel Javanmard et al.

Large language models are commonly trained through multi-stage post-training: first via RLHF, then fine-tuned for other downstream objectives. Yet even small downstream updates can compromise earlier learned behaviors (e.g., safety), exposing a brittleness known as catastrophic forgetting. This suggests standard RLHF objectives do not guarantee robustness to future adaptation. To address it, most prior work designs downstream-time methods to preserve previously learned behaviors. We argue that preventing this requires pre-finetuning robustness: the base policy should avoid brittle high-reward solutions whose reward drops sharply under standard fine-tuning. We propose Fine-tuning Robust Policy Optimization (FRPO), a robust RLHF framework that optimizes reward not only at the current policy, but across a KL-bounded neighborhood of policies reachable by downstream adaptation. The key idea is to ensure reward stability under policy shifts via a max-min formulation. By modifying GRPO, we develop an algorithm with no extra computation, and empirically show it substantially reduces safety degradation across multiple base models and downstream fine-tuning regimes (SFT and RL) while preserving downstream task performance. We further study a math-focused RL setting, demonstrating that FRPO preserves accuracy under subsequent fine-tuning.

Mahdi Sabbaghi, George Pappas, Adel Javanmard et al.

Supervised fine-tuning (SFT) provides the standard approach for teaching LLMs new behaviors from offline expert demonstrations. However, standard SFT uniformly fits all samples -- including those with low likelihood under the base model -- which can disproportionately drive training updates toward overfitting specific samples rather than learning the target behavior. Moreover, adapting to these unlikely samples induces substantial policy shifts that degrade prior capabilities. Existing methods mitigate this by filtering, regenerating, or down-weighting low-likelihood data. In doing so, they often suppress precisely the novel behaviors the base model has yet to learn. We propose InfoSFT, a principled weighting scheme for the SFT objective that concentrates learning signals on maximally informative, medium-confidence tokens -- those neither overly familiar to the base model nor too unlikely to cause instability. Requiring only a one-line modification to the standard token-wise loss, InfoSFT demonstrably improves generalization over vanilla SFT and likelihood-weighted baselines across math, code, and chain-of-thought tasks with diverse model families, while better preserving pre-existing capabilities.

Shayan Kiyani, George Pappas, Hamed Hassani

Conditional validity and length efficiency are two crucial aspects of conformal prediction (CP). Conditional validity ensures accurate uncertainty quantification for data subpopulations, while proper length efficiency ensures that the prediction sets remain informative. Despite significant efforts to address each of these issues individually, a principled framework that reconciles these two objectives has been missing in the CP literature. In this paper, we develop Conformal Prediction with Length-Optimization (CPL) - a novel and practical framework that constructs prediction sets with (near-) optimal length while ensuring conditional validity under various classes of covariate shifts, including the key cases of marginal and group-conditional coverage. In the infinite sample regime, we provide strong duality results which indicate that CPL achieves conditional validity and length optimality. In the finite sample regime, we show that CPL constructs conditionally valid prediction sets. Our extensive empirical evaluations demonstrate the superior prediction set size performance of CPL compared to state-of-the-art methods across diverse real-world and synthetic datasets in classification, regression, and large language model-based multiple choice question answering. An Implementation of our algorithm can be accessed at the following link: https://github.com/shayankiyani98/CP.

Shayan Kiyani, George Pappas, Hamed Hassani

In this paper, we focus on the problem of conformal prediction with conditional guarantees. Prior work has shown that it is impossible to construct nontrivial prediction sets with full conditional coverage guarantees. A wealth of research has considered relaxations of full conditional guarantees, relying on some predefined uncertainty structures. Departing from this line of thinking, we propose Partition Learning Conformal Prediction (PLCP), a framework to improve conditional validity of prediction sets through learning uncertainty-guided features from the calibration data. We implement PLCP efficiently with alternating gradient descent, utilizing off-the-shelf machine learning models. We further analyze PLCP theoretically and provide conditional guarantees for infinite and finite sample sizes. Finally, our experimental results over four real-world and synthetic datasets show the superior performance of PLCP compared to state-of-the-art methods in terms of coverage and length in both classification and regression scenarios.

Mahdi Sabbaghi, Paul Kassianik, George Pappas et al.

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new methodologies for optimizing models to achieve high performance on hard tasks. In this paper, we apply these advances to the task of model jailbreaking: eliciting harmful responses from aligned LLMs. We develop an adversarial reasoning approach to automatic jailbreaking that leverages a loss signal to guide the test-time compute, achieving SOTA attack success rates against many aligned LLMs, even those that aim to trade inference-time compute for adversarial robustness. Our approach introduces a new paradigm in understanding LLM vulnerabilities, laying the foundation for the development of more robust and trustworthy AI systems.

Shayan Kiyani, George Pappas, Aaron Roth et al.

A fundamental question in data-driven decision making is how to quantify the uncertainty of predictions in ways that can usefully inform downstream action. This interface between prediction uncertainty and decision-making is especially important in risk-sensitive domains, such as medicine. In this paper, we develop decision-theoretic foundations that connect uncertainty quantification using prediction sets with risk-averse decision-making. Specifically, we answer three fundamental questions: (1) What is the correct notion of uncertainty quantification for risk-averse decision makers? We prove that prediction sets are optimal for decision makers who wish to optimize their value at risk. (2) What is the optimal policy that a risk averse decision maker should use to map prediction sets to actions? We show that a simple max-min decision policy is optimal for risk-averse decision makers. Finally, (3) How can we derive prediction sets that are optimal for such decision makers? We provide an exact characterization in the population regime and a distribution free finite-sample construction. Answering these questions naturally leads to an algorithm, Risk-Averse Calibration (RAC), which follows a provably optimal design for deriving action policies from predictions. RAC is designed to be both practical-capable of leveraging the quality of predictions in a black-box manner to enhance downstream utility-and safe-adhering to a user-defined risk threshold and optimizing the corresponding risk quantile of the user's downstream utility. Finally, we experimentally demonstrate the significant advantages of RAC in applications such as medical diagnosis and recommendation systems. Specifically, we show that RAC achieves a substantially improved trade-off between safety and utility, offering higher utility compared to existing methods while maintaining the safety guarantee.

Sima Noorani, Shayan Kiyani, George Pappas et al.

Uncertainty quantification (UQ) is essential for safe deployment of generative AI models such as large language models (LLMs), especially in high stakes applications. Conformal prediction (CP) offers a principled uncertainty quantification framework, but classical methods focus on regression and classification, relying on geometric distances or softmax scores: tools that presuppose structured outputs. We depart from this paradigm by studying CP in a query only setting, where prediction sets must be constructed solely from finite queries to a black box generative model, introducing a new trade off between coverage, test time query budget, and informativeness. We introduce Conformal Prediction with Query Oracle (CPQ), a framework characterizing the optimal interplay between these objectives. Our finite sample algorithm is built on two core principles: one governs the optimal query policy, and the other defines the optimal mapping from queried samples to prediction sets. Remarkably, both are rooted in the classical missing mass problem in statistics. Specifically, the optimal query policy depends on the rate of decay, or the derivative, of the missing mass, for which we develop a novel estimator. Meanwhile, the optimal mapping hinges on the missing mass itself, which we estimate using Good Turing estimators. We then turn our focus to implementing our method for language models, where outputs are vast, variable, and often under specified. Fine grained experiments on three real world open ended tasks and two LLMs, show CPQ applicability to any black box LLM and highlight: (1) individual contribution of each principle to CPQ performance, and (2) CPQ ability to yield significantly more informative prediction sets than existing conformal methods for language uncertainty quantification.

Sunay Joshi, Shayan Kiyani, George Pappas et al.

We consider the problem of conformal prediction under covariate shift. Given labeled data from a source domain and unlabeled data from a covariate shifted target domain, we seek to construct prediction sets with valid marginal coverage in the target domain. Most existing methods require estimating the unknown likelihood ratio function, which can be prohibitive for high-dimensional data such as images. To address this challenge, we introduce the likelihood ratio regularized quantile regression (LR-QR) algorithm, which combines the pinball loss with a novel choice of regularization in order to construct a threshold function without directly estimating the unknown likelihood ratio. We show that the LR-QR method has coverage at the desired level in the target domain, up to a small error term that we can control. Our proofs draw on a novel analysis of coverage via stability bounds from learning theory. Our experiments demonstrate that the LR-QR algorithm outperforms existing methods on high-dimensional prediction tasks, including a regression task for the Communities and Crime dataset, an image classification task from the WILDS repository, and an LLM question-answering task on the MMLU benchmark.

Nikolaos Bousias, Stefanos Pertigkiozoglou, Kostas Daniilidis et al.

Multi-agent reinforcement learning has emerged as a powerful framework for enabling agents to learn complex, coordinated behaviors but faces persistent challenges regarding its generalization, scalability and sample efficiency. Recent advancements have sought to alleviate those issues by embedding intrinsic symmetries of the systems in the policy. Yet, most dynamical systems exhibit little to no symmetries to exploit. This paper presents a novel framework for embedding extrinsic symmetries in multi-agent system dynamics that enables the use of symmetry-enhanced methods to address systems with insufficient intrinsic symmetries, expanding the scope of equivariant learning to a wide variety of MARL problems. Central to our framework is the Group Equivariant Graphormer, a group-modular architecture specifically designed for distributed swarming tasks. Extensive experiments on a swarm of symmetry-breaking quadrotors validate the effectiveness of our approach, showcasing its potential for improved generalization and zero-shot scalability. Our method achieves significant reductions in collision rates and enhances task success rates across a diverse range of scenarios and varying swarm sizes.

Nikolaos Bousias, Lars Lindemann, George Pappas

We study the effect of group symmetrization of pre-trained models on conformal prediction (CP), a post-hoc, distribution-free, finite-sample method of uncertainty quantification that offers formal coverage guarantees under the assumption of data exchangeability. Unfortunately, CP uncertainty regions can grow significantly in long horizon missions, rendering the statistical guarantees uninformative. To that end, we propose infusing CP with geometric information via group-averaging of the pretrained predictor to distribute the non-conformity mass across the orbits. Each sample now is treated as a representative of an orbit, thus uncertainty can be mitigated by other samples entangled to it via the orbit inducing elements of the symmetry group. Our approach provably yields contracted non-conformity scores in increasing convex order, implying improved exponential-tail bounds and sharper conformal prediction sets in expectation, especially at high confidence levels. We then propose an experimental design to test these theoretical claims in pedestrian trajectory prediction.

Sima Noorani, Shayan Kiyani, George Pappas et al.

AI predictive systems are increasingly embedded in decision making pipelines, shaping high stakes choices once made solely by humans. Yet robust decisions under uncertainty still rely on capabilities that current AI lacks: domain knowledge not captured by data, long horizon context, and reasoning grounded in the physical world. This gap has motivated growing efforts to design collaborative frameworks that combine the complementary strengths of humans and AI. This work advances this vision by identifying the fundamental principles of Human AI collaboration within uncertainty quantification, a key component of reliable decision making. We introduce Human AI Collaborative Uncertainty Quantification, a framework that formalizes how an AI model can refine a human expert's proposed prediction set with two goals: avoiding counterfactual harm, ensuring the AI does not degrade correct human judgments, and complementarity, enabling recovery of correct outcomes the human missed. At the population level, we show that the optimal collaborative prediction set follows an intuitive two threshold structure over a single score function, extending a classical result in conformal prediction. Building on this insight, we develop practical offline and online calibration algorithms with provable distribution free finite sample guarantees. The online method adapts to distribution shifts, including human behavior evolving through interaction with AI, a phenomenon we call Human to AI Adaptation. Experiments across image classification, regression, and text based medical decision making show that collaborative prediction sets consistently outperform either agent alone, achieving higher coverage and smaller set sizes across various conditions.

Shayan Kiyani, Hamed Hassani, George Pappas et al.

Calibration has emerged as a foundational goal in ``trustworthy machine learning'', in part because of its strong decision theoretic semantics. Independent of the underlying distribution, and independent of the decision maker's utility function, calibration promises that amongst all policies mapping predictions to actions, the uniformly best policy is the one that ``trusts the predictions'' and acts as if they were correct. But this is true only of \emph{fully calibrated} forecasts, which are tractable to guarantee only for very low dimensional prediction problems. For higher dimensional prediction problems (e.g. when outcomes are multiclass), weaker forms of calibration have been studied that lack these decision theoretic properties. In this paper we study how a conservative decision maker should map predictions endowed with these weaker (``partial'') calibration guarantees to actions, in a way that is robust in a minimax sense: i.e. to maximize their expected utility in the worst case over distributions consistent with the calibration guarantees. We characterize their minimax optimal decision rule via a duality argument, and show that surprisingly, ``trusting the predictions and acting accordingly'' is recovered in this minimax sense by \emph{decision calibration} (and any strictly stronger notion of calibration), a substantially weaker and more tractable condition than full calibration. For calibration guarantees that fall short of decision calibration, the minimax optimal decision rule is still efficiently computable, and we provide an empirical evaluation of a natural one that applies to any regression model solved to optimize squared error.

Mahdi Sabbaghi, George Pappas, Hamed Hassani et al.

Despite the success of Transformers on language understanding, code generation, and logical reasoning, they still fail to generalize over length on basic arithmetic tasks such as addition and multiplication. A major reason behind this failure is the vast difference in structure between numbers and text; For example, the numbers are typically parsed from right to left, and there is a correspondence between digits at the same position across different numbers. In contrast, for text, such symmetries are quite unnatural. In this work, we propose to encode these semantics explicitly into the model via modified number formatting and custom positional encodings. Empirically, our method allows a Transformer trained on numbers with at most 5-digits for addition and multiplication to generalize up to 50-digit numbers, without using additional data for longer sequences. We further demonstrate that traditional absolute positional encodings (APE) fail to generalize to longer sequences, even when trained with augmented data that captures task symmetries. To elucidate the importance of explicitly encoding structure, we prove that explicit incorporation of structure via positional encodings is necessary for out-of-distribution generalization. Finally, we pinpoint other challenges inherent to length generalization beyond capturing symmetries, in particular complexity of the underlying task, and propose changes in the training distribution to address them.

Aritra Mitra, Hamed Hassani, George Pappas

We study a federated variant of the best-arm identification problem in stochastic multi-armed bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via a server to identify the best arm (i.e., the arm with the highest mean reward) with prescribed confidence. For this problem, we propose Fed-SEL, a simple communication-efficient algorithm that builds on successive elimination techniques and involves local sampling steps at the clients. To study the performance of Fed-SEL, we introduce a notion of arm-heterogeneity that captures the level of dissimilarity between distributions of arms corresponding to different clients. Interestingly, our analysis reveals the benefits of arm-heterogeneity in reducing both the sample- and communication-complexity of Fed-SEL. As a special case of our analysis, we show that for certain heterogeneous problem instances, Fed-SEL outputs the best-arm after just one round of communication. Our findings have the following key implication: unlike federated supervised learning where recent work has shown that statistical heterogeneity can lead to poor performance, one can provably reap the benefits of both local computation and heterogeneity for federated best-arm identification. As our final contribution, we develop variants of Fed-SEL, both for federated and peer-to-peer settings, that are robust to the presence of Byzantine clients, and hence suitable for deployment in harsh, adversarial environments.

Paraskevi Nousi, Styliani-Christina Fragkouli, Nikolaos Passalis et al.

Recently, artificial neural networks have been gaining momentum in the field of gravitational wave astronomy, for example in surrogate modelling of computationally expensive waveform models for binary black hole inspiral and merger. Surrogate modelling yields fast and accurate approximations of gravitational waves and neural networks have been used in the final step of interpolating the coefficients of the surrogate model for arbitrary waveforms outside the training sample. We investigate the existence of underlying structures in the empirical interpolation coefficients using autoencoders. We demonstrate that when the coefficient space is compressed to only two dimensions, a spiral structure appears, wherein the spiral angle is linearly related to the mass ratio. Based on this finding, we design a spiral module with learnable parameters, that is used as the first layer in a neural network, which learns to map the input space to the coefficients. The spiral module is evaluated on multiple neural network architectures and consistently achieves better speed-accuracy trade-off than baseline models. A thorough experimental study is conducted and the final result is a surrogate model which can evaluate millions of input parameters in a single forward pass in under 1ms on a desktop GPU, while the mismatch between the corresponding generated waveforms and the ground-truth waveforms is better than the compared baseline methods. We anticipate the existence of analogous underlying structures and corresponding computational gains also in the case of spinning black hole binaries.

Matthew Malencia, Vijay Kumar, George Pappas et al.

We study the consideration of fairness in redundant assignment for multi-agent task allocation. It has recently been shown that redundant assignment of agents to tasks provides robustness to uncertainty in task performance. However, the question of how to fairly assign these redundant resources across tasks remains unaddressed. In this paper, we present a novel problem formulation for fair redundant task allocation, which we cast as the optimization of worst-case task costs under a cardinality constraint. Solving this problem optimally is NP-hard. We exploit properties of supermodularity to propose a polynomial-time, near-optimal solution. In supermodular redundant assignment, the use of additional agents always improves task costs. Therefore, we provide a solution set that is $α$ times larger than the cardinality constraint. This constraint relaxation enables our approach to achieve a super-optimal cost by using a sub-optimal assignment size. We derive the sub-optimality bound on this cardinality relaxation, $α$. Additionally, we demonstrate that our algorithm performs near-optimally without the cardinality relaxation. We show simulations of redundant assignments of robots to goal nodes on transport networks with uncertain travel times. Empirically, our algorithm outperforms benchmarks, scales to large problems, and provides improvements in both fairness and average utility.

Ke Sun, Brent Schlotfeldt, George Pappas et al.

In this paper, we address the problem of stochastic motion planning under partial observability, more specifically, how to navigate a mobile robot equipped with continuous range sensors such as LIDAR. In contrast to many existing robotic motion planning methods, we explicitly consider the uncertainty of the robot state by modeling the system as a POMDP. Recent work on general purpose POMDP solvers is typically limited to discrete observation spaces, and does not readily apply to the proposed problem due to the continuous measurements from LIDAR. In this work, we build upon an existing Monte Carlo Tree Search method, POMCP, and propose a new algorithm POMCP++. Our algorithm can handle continuous observation spaces with a novel measurement selection strategy. The POMCP++ algorithm overcomes over-optimism in the value estimation of a rollout policy by removing the implicit perfect state assumption at the rollout phase. We validate POMCP++ in theory by proving it is a Monte Carlo Tree Search algorithm. Through comparisons with other methods that can also be applied to the proposed problem, we show that POMCP++ yields significantly higher success rate and total reward.

Anastasios Tsiamis, George Pappas

In this paper, we consider the problem of predicting observations generated online by an unknown, partially observed linear system, which is driven by stochastic noise. For such systems the optimal predictor in the mean square sense is the celebrated Kalman filter, which can be explicitly computed when the system model is known. When the system model is unknown, we have to learn how to predict observations online based on finite data, suffering possibly a non-zero regret with respect to the Kalman filter's prediction. We show that it is possible to achieve a regret of the order of $\mathrm{poly}\log(N)$ with high probability, where $N$ is the number of observations collected. Our work is the first to provide logarithmic regret guarantees for the widely used Kalman filter. This is achieved using an online least-squares algorithm, which exploits the approximately linear relation between future observations and past observations. The regret analysis is based on the stability properties of the Kalman filter, recent statistical tools for finite sample analysis of system identification, and classical results for the analysis of least-squares algorithms for time series. Our regret analysis can also be applied for state prediction of the hidden state, in the case of unknown noise statistics but known state-space basis. A fundamental technical contribution is that our bounds hold even for the class of non-explosive systems, which includes the class of marginally stable systems, which was an open problem for the case of online prediction under stochastic noise.

Ekaterina Tolstaya, Fernando Gama, James Paulos et al.

We consider the problem of finding distributed controllers for large networks of mobile robots with interacting dynamics and sparsely available communications. Our approach is to learn local controllers that require only local information and communications at test time by imitating the policy of centralized controllers using global information at training time. By extending aggregation graph neural networks to time varying signals and time varying network support, we learn a single common local controller which exploits information from distant teammates using only local communication interchanges. We apply this approach to the problem of flocking to demonstrate performance on communication graphs that change as the robots move. We examine how a decreasing communication radius and faster velocities increase the value of multi-hop information.

Anastasios Tsiamis, Konstantinos Gatsis, George Pappas

This paper studies the problem of remote state estimation in the presence of a passive eavesdropper. A sensor measures a linear plant's state and transmits it to an authorized user over a packet-dropping channel, which is susceptible to eavesdropping. Our goal is to design a coding scheme such that the eavesdropper cannot infer the plant's current state, while the user successfully decodes the sent messages. We employ a novel class of codes, termed State-Secrecy Codes, which are fast and efficient for dynamical systems. They apply linear time-varying transformations to the current and past states received by the user. In this way, they force the eavesdropper's information matrix to decrease with asymptotically the same rate as in the open-loop prediction case, i.e. when the eavesdropper misses all messages. As a result, the eavesdropper's minimum mean square error (mmse) for the unstable states grows unbounded, while the respective error for the stable states converges to the open-loop prediction one. These secrecy guarantees are achieved under minimal conditions, which require that, at least once, the user receives the corresponding packet while the eavesdropper fails to intercept it. Meanwhile, the user's estimation performance remains optimal. The theoretical results are illustrated in simulations.

Fragkiskos Koufogiannis, George Pappas

The emergence of social and technological networks has enabled rapid sharing of data and information. This has resulted in significant privacy concerns where private information can be either leaked or inferred from public data. The problem is significantly harder for social networks where we may reveal more information to our friends than to strangers. Nonetheless, our private information can still leak to strangers as our friends are their friends and so on. In order to address this important challenge, in this paper, we present a privacy-preserving mechanism that enables private data to be diffused over a network. In particular, whenever a user wants to access another users' data, the proposed mechanism returns a differentially private response that ensures that the amount of private data leaked depends on the distance between the two users in the network. While allowing global statistics to be inferred by users acting as analysts, our mechanism guarantees that no individual user, or a group of users, can harm the privacy guarantees of any other user. We illustrate our mechanism with two examples: one on synthetic data where the users share their GPS coordinates; and one on a Facebook ego-network where a user shares her infection status.