arXiv subjects

David Smith

Publications and source records attributed to David Smith.

At least 55 records · Page 3Linked to original sources

arXiv2020

Model Elicitation through Direct Questioning

The future will be replete with scenarios where humans are robots will be working together in complex environments. Teammates interact, and the robot's interaction has to be about getting useful information about the human's (teammate's) model. There are many challenges before a robot can interact, such as incorporating the structural differences in the human's model, ensuring simpler responses, etc. In this paper, we investigate how a robot can interact to localize the human model from a set of models. We show how to generate questions to refine the robot's understanding of the teammate's model. We evaluate the method in various planning domains. The evaluation shows that these questions can be generated offline, and can help refine the model through simple answers.

cs.AI↗

arXiv2020

Designing Environments Conducive to Interpretable Robot Behavior

Designing robots capable of generating interpretable behavior is a prerequisite for achieving effective human-robot collaboration. This means that the robots need to be capable of generating behavior that aligns with human expectations and, when required, provide explanations to the humans in the loop. However, exhibiting such behavior in arbitrary environments could be quite expensive for robots, and in some cases, the robot may not even be able to exhibit the expected behavior. Given structured environments (like warehouses and restaurants), it may be possible to design the environment so as to boost the interpretability of the robot's behavior or to shape the human's expectations of the robot's behavior. In this paper, we investigate the opportunities and limitations of environment design as a tool to promote a type of interpretable behavior -- known in the literature as explicable behavior. We formulate a novel environment design framework that considers design over multiple tasks and over a time horizon. In addition, we explore the longitudinal aspect of explicable behavior and the trade-off that arises between the cost of design and the cost of generating explicable behavior over a time horizon.

cs.AI↗

arXiv2020

The Cost of Privacy in Asynchronous Differentially-Private Machine Learning

We consider training machine learning models using Training data located on multiple private and geographically-scattered servers with different privacy settings. Due to the distributed nature of the data, communicating with all collaborating private data owners simultaneously may prove challenging or altogether impossible. In this paper, we develop differentially-private asynchronous algorithms for collaboratively training machine-learning models on multiple private datasets. The asynchronous nature of the algorithms implies that a central learner interacts with the private data owners one-on-one whenever they are available for communication without needing to aggregate query responses to construct gradients of the entire fitness function. Therefore, the algorithm efficiently scales to many data owners. We define the cost of privacy as the difference between the fitness of a privacy-preserving machine-learning model and the fitness of trained machine-learning model in the absence of privacy concerns. We prove that we can forecast the performance of the proposed privacy-preserving asynchronous algorithms. We demonstrate that the cost of privacy has an upper bound that is inversely proportional to the combined size of the training datasets squared and the sum of the privacy budgets squared. We validate the theoretical results with experiments on financial and medical datasets. The experiments illustrate that collaboration among more than 10 data owners with at least 10,000 records with privacy budgets greater than or equal to 1 results in a superior machine-learning model in comparison to a model trained in isolation on only one of the datasets, illustrating the value of collaboration and the cost of the privacy. The number of the collaborating datasets can be lowered if the privacy budget is higher.

cs.LG↗

arXiv2020

Peer-to-Peer Trading in Electricity Networks: An Overview

Peer-to-peer trading is a next-generation energy management technique that economically benefits proactive consumers (prosumers) transacting their energy as goods and services. At the same time, peer-to-peer energy trading is also expected to help the grid by reducing peak demand, lowering reserve requirements, and curtailing network loss. However, large-scale deployment of peer-to-peer trading in electricity networks poses a number of challenges in modeling transactions in both the virtual and physical layers of the network. As such, this article provides a comprehensive review of the state-of-the-art in research on peer-to-peer energy trading techniques. By doing so, we provide an overview of the key features of peer-to-peer trading and its benefits of relevance to the grid and prosumers. Then, we systematically classify the existing research in terms of the challenges that the studies address in the virtual and the physical layers. We then further identify and discuss those technical approaches that have been extensively used to address the challenges in peer-to-peer transactions. Finally, the paper is concluded with potential future research directions.

cs.MA↗

arXiv2019

Report on the First HIPstIR Workshop on the Future of Information Retrieval

The vision of HIPstIR is that early stage information retrieval (IR) researchers get together to develop a future for non-mainstream ideas and research agendas in IR. The first iteration of this vision materialized in the form of a three day workshop in Portsmouth, New Hampshire attended by 24 researchers across academia and industry. Attendees pre-submitted one or more topics that they want to pitch at the meeting. Then over the three days during the workshop, we self-organized into groups and worked on six specific proposals of common interest. In this report, we present an overview of the workshop and brief summaries of the six proposals that resulted from the workshop.

cs.IR↗

arXiv2019

Representation theory of partial relation extensions

Let C be a finite dimensional algebra of global dimension at most two. A partial relation extension is any trivial extension of C by a direct summand of its relation C-C-bimodule. When C is a tilted algebra, this construction provides an intermediate class of algebras between tilted and cluster tilted algebras. The text investigates the representation theory of partial relation extensions. When C is tilted, any complete slice in the Auslander-Reiten quiver of C embeds as a local slice in the Auslander-Reiten quiver of the partial relation extension; Moreover, a systematic way of producing partial relation extensions is introduced by considering direct sum decompositions of the potential arising from a minimal system of relations of C.

math.RT↗

arXiv2019

FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second

Current methods for body shape estimation either lack detail or require many images. They are usually architecturally complex and computationally expensive. We propose FACSIMILE (FAX), a method that estimates a detailed body from a single photo, lowering the bar for creating virtual representations of humans. Our approach is easy to implement and fast to execute, making it easily deployable. FAX uses an image-translation network which recovers geometry at the original resolution of the image. Counterintuitively, the main loss which drives FAX is on per-pixel surface normals instead of per-pixel depth, making it possible to estimate detailed body geometry without any depth supervision. We evaluate our approach both qualitatively and quantitatively, and compare with a state-of-the-art method.

cs.CV↗

arXiv2019

Switch-based Hybrid Beamforming for Massive MIMO Communications in mmWave Bands

Switch-based hybrid network is a promising implementation for beamforming in large-scale millimetre wave (mmWave) antenna arrays. By fully exploiting the sparse nature of the mmWave channel, such hybrid beamforming reduces complexity and power consumption when compared with a structure based on phase shifters. However, the difficulty of designing an optimum beamformer in the analog domain is prohibitive due to the binary nature of such a switch-based structure. Thus, here we propose a new method for designing a switch-based hybrid beamformer for massive MIMO communications in mmWave bands. We first propose a method for decoupling the joint optimization of analog and digital beamformers by confining the problem to a rank-constrained subspace. We then approximate the solution through two approaches: norm maximization (SHD-NM), and majorization (SHD-QRQU). In the norm maximization method, we propose a modified sequential convex programming (SCP) procedure that maximizes the mutual information while addressing the mismatch incurred from approximating the log-determinant by a Frobenius norm. In the second method, we employ a lower bound on the mutual information by QR factorization. We also introduce linear constraints in order to include frequently-used partially-connected structures. Finally, we show the feasibility, and effectiveness of the proposed methods through several numerical examples. The results demonstrate ability of the proposed methods to track closely the spectral efficiency provided by unconstrained optimal beamformer and phase shifting hybrid beamformer, and outperform a competitor switch-based hybrid beamformer.

eess.SP↗

arXiv2019

Linear Dispersive Shocks

We present a linear dispersive partial differential equation which manifests a number of qualitative features of dispersive shocks, typically thought to occur only in nonlinear models. The model captures much of the short time phenomenon but deviates from the full nonlinear model in its long time behavior. Though we limit our present discussion to dispersive shocks occurring in the Korteweg-de Vries equation, our work extends readily to other higher order dispersive models too.

math.AP↗

arXiv2019

Stability Conditions and Maximal Green Sequences in Abelian Categories

In this paper we study the stability functions on abelian categories introduced by Rudakov in \cite{Ru} and their relation with torsion classes and maximal green sequences. Moreover we introduce a new kind of stability function which is compatible with the wall and chamber of the category.

math.RT↗

arXiv2019

Towards Explainable AI Planning as a Service

Explainable AI is an important area of research within which Explainable Planning is an emerging topic. In this paper, we argue that Explainable Planning can be designed as a service -- that is, as a wrapper around an existing planning system that utilises the existing planner to assist in answering contrastive questions. We introduce a prototype framework to facilitate this, along with some examples of how a planner can be used to address certain types of contrastive questions. We discuss the main advantages and limitations of such an approach and we identify open questions for Explainable Planning as a service that identify several possible research directions.

cs.AI↗

arXiv2019

Wall and Chamber Structure for finite-dimensional Algebras

We use $τ$-tilting theory to give a description of the wall and chamber structure of a finite dimensional algebra. We also study $\mathfrak{D}$-generic paths in the wall and chamber structure of an algebra $A$ and show that every maximal green sequence in mod $A$ is induced by a $\mathfrak{D}$-generic path.

math.RT↗

arXiv2019

LookUP: Vision-Only Real-Time Precise Underground Localisation for Autonomous Mining Vehicles

A key capability for autonomous underground mining vehicles is real-time accurate localisation. While significant progress has been made, currently deployed systems have several limitations ranging from dependence on costly additional infrastructure to failure of both visual and range sensor-based techniques in highly aliased or visually challenging environments. In our previous work, we presented a lightweight coarse vision-based localisation system that could map and then localise to within a few metres in an underground mining environment. However, this level of precision is insufficient for providing a cheaper, more reliable vision-based automation alternative to current range sensor-based systems. Here we present a new precision localisation system dubbed "LookUP", which learns a neural-network-based pixel sampling strategy for estimating homographies based on ceiling-facing cameras without requiring any manual labelling. This new system runs in real time on limited computation resource and is demonstrated on two different underground mine sites, achieving real time performance at ~5 frames per second and a much improved average localisation error of ~1.2 metre.

cs.RO↗

arXiv2019

The Value of Collaboration in Convex Machine Learning with Differential Privacy

In this paper, we apply machine learning to distributed private data owned by multiple data owners, entities with access to non-overlapping training datasets. We use noisy, differentially-private gradients to minimize the fitness cost of the machine learning model using stochastic gradient descent. We quantify the quality of the trained model, using the fitness cost, as a function of privacy budget and size of the distributed datasets to capture the trade-off between privacy and utility in machine learning. This way, we can predict the outcome of collaboration among privacy-aware data owners prior to executing potentially computationally-expensive machine learning algorithms. Particularly, we show that the difference between the fitness of the trained machine learning model using differentially-private gradient queries and the fitness of the trained machine model in the absence of any privacy concerns is inversely proportional to the size of the training datasets squared and the privacy budget squared. We successfully validate the performance prediction with the actual performance of the proposed privacy-aware learning algorithms, applied to: financial datasets for determining interest rates of loans using regression; and detecting credit card frauds using support vector machines.

cs.CR↗

arXiv2019

Multi-stage Antenna Selection for Adaptive Beamforming in MIMO Arrays

Increasing the number of transmit and receive elements in multiple-input-multiple-output (MIMO) antenna arrays imposes a substantial increase in hardware and computational costs. We mitigate this problem by employing a reconfigurable MIMO array where large transmit and receive arrays are multiplexed in a smaller set of k baseband signals. We consider four stages for the MIMO array configuration and propose four different selection strategies to offer dimensionality reduction in post-processing and achieve hardware cost reduction in digital signal processing (DSP) and radio-frequency (RF) stages. We define the problem as a determinant maximization and develop a unified formulation to decouple the joint problem and select antennas/elements in various stages in one integrated problem. We then analyze the performance of the proposed selection approaches and prove that, in terms of the output SINR, a joint transmit-receive selection method performs best followed by matched-filter, hybrid and factored selection methods. The theoretical results are validated numerically, demonstrating that all methods allow an excellent trade-off between performance and cost.

eess.SP↗

arXiv2019

Why Couldn't You do that? Explaining Unsolvability of Classical Planning Problems in the Presence of Plan Advice

Explainable planning is widely accepted as a prerequisite for autonomous agents to successfully work with humans. While there has been a lot of research on generating explanations of solutions to planning problems, explaining the absence of solutions remains an open and under-studied problem, even though such situations can be the hardest to understand or debug. In this paper, we show that hierarchical abstractions can be used to efficiently generate reasons for unsolvability of planning problems. In contrast to related work on computing certificates of unsolvability, we show that these methods can generate compact, human-understandable reasons for unsolvability. Empirical analysis and user studies show the validity of our methods as well as their computational efficacy on a number of benchmark planning domains.

cs.AI↗

arXiv2019

Attaining Fairness in Communication for Omniscience

This paper studies how to attain fairness in communication for omniscience, where a set of users exchange their observations of a discrete multiple random source to attain omniscience---the state that all users recover the entire source. The optimal rate region containing all source coding rate vectors that achieve the omniscience with the minimum sum rate is shown to coincide with the core (the solution set) of a coalitional game. Two game-theoretic fairness solutions are studied: the Shapley value and the egalitarian solution. It is shown that the Shapley value assigns each user the source coding rate measured by his/her remaining information of the multiple source given the common randomness that is shared by all users, while the egalitarian solution simply distributes the rates as evenly as possible in the core. To avoid the exponentially growing complexity of obtaining the Shapley value, a polynomial-time approximation method is proposed by utilizing the fact that the Shapley value is the mean value over all extreme points in the core. In addition, a steepest descent algorithm is proposed which converges in polynomial time to the fractional egalitarian solution in the core that can be implemented by network coding schemes. Finally, it is shown that the game can be decomposed into subgames so that both the Shapley value and the egalitarian solution can be obtained within each subgame in a distributed manner with reduced complexity.

cs.IT↗

arXiv2018

Simultaneous Parameter Estimation and Variable Selection via the LN-CASS Prior

We introduce a Bayesian prior distribution, the Logit-Normal continuous analogue of the spike-and-slab (LN-CASS), which enables flexible parameter estimation and variable/model selection in a variety of settings. We demonstrate its use and efficacy in three case studies -- a simulation study and two studies on real biological data from the fields of metabolomics and genomics. The prior allows the use of classical statistical models, which are easily interpretable and well-known to applied scientists, but performs comparably to common machine learning methods in terms of generalisability to previously unseen data.

stat.AP↗