arXiv subjects

John Foley

Publications and source records attributed to John Foley.

12 recordsLinked to original sources

arXiv2025

A Dimension-Reduced Multivariate Spatial Model for Extreme Events: Balancing Flexibility and Scalability

Modeling extreme precipitation and temperature is vital for understanding the impacts of climate change, as hazards like intense rainfall and record-breaking temperatures can result in severe consequences, including floods, droughts, and wildfires. Gaining insight into the spatial variation and interactions between these extremes is critical for effective risk management, early warning systems, and informed policy-making. However, challenges such as the rarity of extreme events, spatial dependencies, and complex cross-variable interactions hinder accurate modeling. We introduce a novel framework for modeling spatial extremes, building upon spatial generalized extreme value (GEV) models. Our approach incorporates a dimension-reduced latent spatial process to improve scalability and flexibility, particularly in capturing asymmetry in cross-covariance structures. This Joint Latent Spatial GEV model (JLS-GEV) overcomes key limitations of existing methods by providing a more flexible framework for inter-variable dependencies. In addition to addressing event rarity, spatial dependence and cross-variable interactions, JLS-GEV supports nonstationary spatial behaviors and independently collected data sources, while maintaining practical fitting times through dimension reduction. We validate JLS-GEV through extensive simulation studies, demonstrating its superior performance in capturing spatial extremes compared to baseline modeling approaches. Application to real-world data on extreme precipitation and temperature in the southeastern United States highlights its practical utility. While primarily motivated by environmental challenges, this framework is broadly applicable to interdisciplinary studies of spatial extremes in interdependent natural processes.

stat.ME↗

arXiv2020

Operads for Designing Systems of Systems

System of systems engineering seeks to analyze, design and deploy collections of systems that together can flexibly address an array of complex tasks. In the Complex Adaptive System Composition and Design Environment program, we developed "network operads" as a tool for designing and tasking systems of systems, and applied them to domains including maritime search and rescue. The network operad formalism offers new ways to handle changing levels of abstraction in system-of-system design and tasking.

cs.SE↗

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

Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning

Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has gone into addressing opacity, but almost no effort has been devoted to producing high quality environments for experimental evaluation of agent behavior. We present TOYBOX, a new high-performance, open-source* subset of Atari environments re-designed for the experimental evaluation of deep RL. We show that TOYBOX enables a wide range of experiments and analyses that are impossible in other environments. *https://kdl-umass.github.io/Toybox/

cs.LG↗

arXiv2019

Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a single environment. Unfortunately, there are still pernicious sources of variability in reinforcement learning agents that make reporting common summary statistics an unsound metric for performance. Our experiments demonstrate the variability of common agents used in the popular OpenAI Baselines repository. We make the case for reporting post-training agent performance as a distribution, rather than a point estimate.

cs.LG↗

arXiv2019

Network Models from Petri Nets with Catalysts

Petri networks and network models are two frameworks for the compositional design of systems of interacting entities. Here we show how to combine them using the concept of a "catalyst": an entity that is neither destroyed nor created by any process it engages in. In a Petri net, a place is a catalyst if its in-degree equals its out-degree for every transition. We show how a Petri net with a chosen set of catalysts gives a network model. This network model maps any list of catalysts from the chosen set to the category whose morphisms are all the processes enabled by this list of catalysts. Applying the Grothendieck construction, we obtain a category fibered over the category whose objects are lists of catalysts. This category has as morphisms all processes enabled by some list of catalysts. While this category has a symmetric monoidal structure that describes doing processes in parallel, its fibers also have premonoidal structures that describe doing one process and then another while reusing the catalysts.

math.CT↗

arXiv2018

ToyBox: Better Atari Environments for Testing Reinforcement Learning Agents

It is a widely accepted principle that software without tests has bugs. Testing reinforcement learning agents is especially difficult because of the stochastic nature of both agents and environments, the complexity of state-of-the-art models, and the sequential nature of their predictions. Recently, the Arcade Learning Environment (ALE) has become one of the most widely used benchmark suites for deep learning research, and state-of-the-art Reinforcement Learning (RL) agents have been shown to routinely equal or exceed human performance on many ALE tasks. Since ALE is based on emulation of original Atari games, the environment does not provide semantically meaningful representations of internal game state. This means that ALE has limited utility as an environment for supporting testing or model introspection. We propose ToyBox, a collection of reimplementations of these games that solves this critical problem and enables robust testing of RL agents.

cs.AI↗

arXiv2018

Explainable Agreement through Simulation for Tasks with Subjective Labels

The field of information retrieval often works with limited and noisy data in an attempt to classify documents into subjective categories, e.g., relevance, sentiment and controversy. We typically quantify a notion of agreement to understand the difficulty of the labeling task, but when we present final results, we do so using measures that are unaware of agreement or the inherent subjectivity of the task. We propose using user simulation to understand the effect size of this noisy agreement data. By simulating truth and predictions, we can understand the maximum scores a dataset can support: for if a classifier is doing better than a reasonable model of a human, we cannot conclude that it is actually better, but that it may be learning noise present in the dataset. We present a brief case study on controversy detection that concludes that a commonly-used dataset has been exhausted: in order to advance the state-of-the-art, more data must be gathered at the current level of label agreement in order to distinguish between techniques with confidence.

cs.IR↗

arXiv2018

Named Entity Recognition with Extremely Limited Data

Traditional information retrieval treats named entity recognition as a pre-indexing corpus annotation task, allowing entity tags to be indexed and used during search. Named entity taggers themselves are typically trained on thousands or tens of thousands of examples labeled by humans. However, there is a long tail of named entities classes, and for these cases, labeled data may be impossible to find or justify financially. We propose exploring named entity recognition as a search task, where the named entity class of interest is a query, and entities of that class are the relevant "documents". What should that query look like? Can we even perform NER-style labeling with tens of labels? This study presents an exploration of CRF-based NER models with handcrafted features and of how we might transform them into search queries.

cs.IR↗

arXiv2018

On the Equivalence of Generative and Discriminative Formulations of the Sequential Dependence Model

The sequential dependence model (SDM) is a popular retrieval model which is based on the theory of probabilistic graphical models. While it was originally introduced by Metzler and Croft as a Markov Random Field (aka discriminative probabilistic model), in this paper we demonstrate that it is equivalent to a generative probabilistic model. To build an foundation for future retrieval models, this paper details the axiomatic underpinning of the SDM model as discriminative and generative probabilistic model. The only difference arises whether model parameters are estimated in log-space or Multinomial-space. We demonstrate that parameter-estimation with grid-tuning is negatively impacting the generative formulation, an effect that vanishes when parameters are estimated with coordinate-gradient descent. This is concerning, since empirical differences may be falsely attributed to improved models.

cs.IR↗

arXiv2018

Term Relevance Feedback for Contextual Named Entity Retrieval

We address the role of a user in Contextual Named Entity Retrieval (CNER), showing (1) that user identification of important context-bearing terms is superior to automated approaches, and (2) that further gains are possible if the user indicates the relative importance of those terms. CNER is similar in spirit to List Question answering and Entity disambiguation. However, the main focus of CNER is to obtain user feedback for constructing a profile for a class of entities on the fly and use that to retrieve entities from free text. Given a sentence, and an entity selected from that sentence, CNER aims to retrieve sentences that have entities similar to query entity. This paper explores obtaining term relevance feedback and importance weighting from humans in order to improve a CNER system. We report our findings based on the efforts of IR researchers as well as crowdsourced workers.

cs.IR↗

arXiv2017

Network Models

Networks can be combined in various ways, such as overlaying one on top of another or setting two side by side. We introduce "network models" to encode these ways of combining networks. Different network models describe different kinds of networks. We show that each network model gives rise to an operad, whose operations are ways of assembling a network of the given kind from smaller parts. Such operads, and their algebras, can serve as tools for designing networks. Technically, a network model is a lax symmetric monoidal functor from the free symmetric monoidal category on some set to $\mathbf{Cat}$, and the construction of the corresponding operad proceeds via a symmetric monoidal version of the Grothendieck construction.

math.CT↗