Autonomous Underwater Vehicles collect rich multimodal remote sensing data, but robust fusion and classification of heterogeneous sensor streams remains challenging due to noise and habitat variability. We propose a Bayesian multimodal neural network for fusing optical imagery, bathymetry, and side-scan sonar, quantifying epistemic and aleatoric uncertainty to improve classification reliability in complex underwater environments. Our model leverages uncertainty estimates to identify ambiguous predictions and highlight poorly sampled regions, enabling reliable mapping and evaluation of model confidence. We evaluated our model on large-scale Autonomous Underwater Vehicle survey data, achieving 85.5% classification accuracy, surpassing unimodal baselines by ∼ 7%. We provide a preliminary complexity analysis to estimate onboard feasibility, enabling rapid onboard processing for uncertainty-aware habitat classification. We vary the number of Monte Carlo runs to explore the balance between computational cost and uncertainty estimation. We further analyse how spatial context in side-scan and bathymetric imagery affects mapping accuracy, showing that a 30 metre patch size provides the best balance between habitat continuity and boundary delineation. This work demonstrates a scalable, uncertainty-aware multimodal fusion framework, enhancing the reliability and interpretability of underwater classification and mapping. We release the full codebase and trained models via an open-source software library (PyPI: multimodal-auv).

Given a data set of $(x,y)$ pairs, a common learning task is to fit a model predicting $y$ (a label or dependent variable) conditioned on $x$. This paper considers the similar but much less-understood problem of modeling “higher-order” statistics of $y$’s distribution conditioned on $x$. Such statistics are often challenging to estimate using traditional empirical risk minimization (ERM) approaches. We develop and theoretically analyze an ERM-like approach with multi-observation loss functions. We propose four algorithms formalizing the concept of ERM for this problem, two of which have statistical guarantees in settings allowing both slow and fast convergence rates, but which are out-performed empirically by the other two. Empirical results illustrate potential practicality of these algorithms in low dimensions and significant improvement over standard approaches in some settings.

We consider variations of set reconciliation problems where two parties, Alice and Bob, each hold a set of points in a metric space, and the goal is for Bob to conclude with a set of points that is close to Alice's set of points in a well-defined way. This setting has been referred to as robust set reconciliation. In one variation, the goal is for Bob to end with a set of points that is close to Alice's in earth mover's distance, and in another the goal is for Bob to have a point that is close to each of Alice's. The first problem has been studied before; while previous results achieved an $O(d)$ approximation, where d is the dimension of the space, we achieve an $O(łog n)$ approximation, where n is the number of points. The second problem appears new, and here we find schemes that, under certain conditions, use sublinear communication. Our primary novelty is utilizing Invertible Bloom Lookup Tables in combination with locality sensitive hashing. This combination allows us to cope with the geometric setting in a communication-efficient manner.

In compressed sensing, one wishes to acquire an approximately sparse high-dimensional signal x ∈ ℝnvia m ≪ n noisy linear measurements, then later approximately recover x given only those measurement outcomes. Various guarantees have been studied in terms of the notion of approximation in recovery, and some isolated folklore results are known stating that some forms of recovery are stronger than others, via black-box reductions. In this note we provide a general theorem concerning the hierarchy of strengths of various recovery guarantees. As a corollary of this theorem, by reducing from well-known results in the compressed sensing literature, we obtain an efficient ℓp/ℓpscheme for any 0 <; p <; 1 with the fewest number of measurements currently known amongst efficient schemes, improving recent bounds of [1] and with a simpler algorithm and analysis.

We explore a generalization of set reconciliation, where the goal is to reconcile sets of sets. Alice and Bob each have a parent set consisting of s child sets, each containing at most h elements from a universe of size u. They want to reconcile their sets of sets in a scenario where the total number of differences between all of their child sets (under the minimum difference matching between their child sets) is d. We give several algorithms for this problem, and discuss applications to reconciliation problems on graphs, databases, and collections of documents. We specifically focus on graph reconciliation, providing protocols based on sets of sets reconciliation for random graphs from G(n,p) and for forests of rooted trees.

We study loss functions that measure the accuracy of a prediction based on multiple data points simultaneously. To our knowledge, such loss functions have not been studied before in the area of property elicitation or in machine learning more broadly. As compared to traditional loss functions that take only a single data point, these multi-observation loss functions can in some cases drastically reduce the dimensionality of the hypothesis required. In elicitation, this corresponds to requiring many fewer reports; in empirical risk minimization, it corresponds to algorithms on a hypothesis space of much smaller dimension. We explore some examples of the tradeoff between dimensionality and number of observations, give some geometric characterizations and intuition for relating loss functions and the properties that they elicit, and discuss some implications for both elicitation and machine-learning contexts.

We study novel variations of Voronoi games and associated random processes that we call Voronoi choice games. These games provide a rich framework for studying questions regarding the power of small numbers of choices in multi-player, competitive scenarios, and they further lead to many interesting, non-trivial random processes that appear worthy of study. As an example of the type of problem we study, suppose a group of n miners (or players) are staking land claims through the following process: each miner has m associated points independently and uniformly distributed on an underlying space (such as the unit circle, the unit square, or the unit torus), so the kth miner will have associated points p_{k1}, p_{k2}, ..., p_{km}. We generally here think of m as being a small constant, such as 2. Each miner chooses one of these points as the base point for their claim. Each miner obtains mining rights for the area of the square that is closest to their chosen base; that is, they obtain the Voronoi cell corresponding to their chosen point in the Voronoi diagram of the n chosen points. Each player's goal is simply to maximize the amount of land under their control. What can we say about the players’ strategy and the equilibria of such games? In our main result, we derive bounds on the expected number of pure Nash equilibria for a variation of the 1-dimensional game on the circle where a player owns the arc starting from their point and moving clockwise to the next point. This result uses interesting properties of random arc lengths on circles, and demonstrates the challenges in analyzing these kinds of problems. We also provide several other related results. In particular, for the 1-dimensional game on the circle, we show that a pure Nash equilibrium always exists when each player owns the part of the circle nearest to their point, but it is NP-hard to determine whether a pure Nash equilibrium exists in the variant when each player owns the arc starting from their point clockwise to the next point. This last result, in part, motivates our examination of the random setting.

Prior research suggests that people may ask their family and friends for computer help. But what influences whether and how a "helper" will provide help? To answer this question, we conducted a qualitative investigation of people who participated in computer support activities with family and friends in the past year. We describe how factors including maintenance of one's personal identity as a computer expert and accountability to one's social network determine who receives help and the quality of help provided. We also discuss the complex, fractured relationship between the numerous stakeholders involved in the upkeep of home computing infrastructures. Based on our findings, we provide implications for the design of systems to support informal help-giving in residential settings.

Object-oriented concepts such as reuse and encapsulation offer many benefits to application development, particularly in managing complexity and change. All the benefits of OO that apply to the client can apply equally well to the server. However, until recently, these concepts have proven to benefit only the client side. Could there be any intrinsic or conceptual reason for this? Or could it be a result of timing, the availability of the tools, and the conservative restraints that result from the mission-critical nature of server computing?This panel will explore the roles of objects on the server by examining the experiences of the panelists from a technology consumer's perspective. By doing so, we would like to provide insights for corporations that are making decisions on OO technology, point out pitfalls along the way, and identify potential opportunities for technology providers.All panelists have developed production level object servers. The panel will answer the question of whether we are ready for object servers by discussing the following issues:• Different server types: transactional server, data server, application server, web server, etc. Are they really that much different? Which one is the most important kind?• Experience in implementing and maintaining object systems on the server: the configurations of the systems and how they were arrived at; the tools and programming languages used.• Benefits and drawbacks of server object systems.• What's hard? What's easy?• What are the prerequisites for pervasive deployments of objects on the server? (e.g., standards, application types, customer situations, tools, and languages.)• What would be desirable for technology providers (researchers and vendors) to provide? (Tools, languages, execution environments that represents vendor opportunities.)• Practical advice to organizations interested in introducing objects to the server.