More Like this

1. Proactive policing as reinforcement learning

   Kinsman, Dawson; Wong, Tian_An (May 2023, dblp)
2. Communicative Visualizations as a Learning Problem

   https://doi.org/10.1109/TVCG.2020.3030375  

   Adar, Eytan; Lee, Elsie (January 2020, IEEE Transactions on Visualization and Computer Graphics)

   null (Ed.)

   Significant research has provided robust task and evaluation languages for the analysis of exploratory visualizations. Unfortunately, these taxonomies fail when applied to communicative visualizations. Instead, designers often resort to evaluating communicative visualizations from the cognitive efficiency perspective: "can the recipient accurately decode my message/insight?" However, designers are unlikely to be satisfied if the message went 'in one ear and out the other.' The consequence of this inconsistency is that it is difficult to design or select between competing options in a principled way. The problem we address is the fundamental mismatch between how designers want to describe their intent, and the language they have. We argue that visualization designers can address this limitation through a learning lens: that the recipient is a student and the designer a teacher. By using learning objectives, designers can better define, assess, and compare communicative visualizations. We illustrate how the learning-based approach provides a framework for understanding a wide array of communicative goals. To understand how the framework can be applied (and its limitations), we surveyed and interviewed members of the Data Visualization Society using their own visualizations as a probe. Through this study we identified the broad range of objectives in communicative visualizations and the prevalence of certain objective types. 

   more » « less
3. Seeing Learning Sciences Research as Modeling

   Roschelle, Jeremy (January 2021, International Conference of the Learning Sciences)

   de Vries, E; Hod, Y; Ahn, J (Ed.)

   Researchers in the Learning Sciences take two prevalent stances: research as building theories or as developing designs. The connection between theories and designs is most often filled in by methods, but an alternative stance is possible: research as improving models. The modeling stance seeks parsimonious, useful, illuminating descriptions of learning activity systems. Models can help us understand and express how variability (in all its forms) plays into, is enacted during, and results from designed learning activities. Building models often requires employing multiple theories, methods, and design elements; a modeling stance recognizes that our research often elaborates a multi-level systems view. An explicit modeling stance may lead to developing descriptions of complex systems, inviting multi-stakeholder teamwork to improve these systems, integrating advances in learning analytics and educational data mining, and adding to ability of learning sciences research to tackle challenges at scale. 

   more » « less
4. Temporal Difference Learning as Gradient Splitting

   Liu, Rui; Olshevsky, Alex (November 2021, International Conference on Machine Learning (ICML))

   Temporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process. We give a new interpretation of this method in terms of a splitting of the gradient of an appropriately chosen function. As a consequence of this interpretation, convergence proofs for gradient descent can be applied almost verbatim to temporal difference learning. Beyond giving a new, fuller explanation of why temporal difference works, our interpretation also yields improved convergence times. We consider the setting with 1/T^{1/2} step-size, where previous comparable finite-time convergence time bounds for temporal difference learning had the multiplicative factor 1/(1-\gamma) in front of the bound, with γ being the discount factor. We show that a minor variation on TD learning which estimates the mean of the value function separately has a convergence time where 1/(1-\gamma) only multiplies an asymptotically negligible term. 

   more » « less
5. Ensemble Learning as a Peer Process

   Beikihassan, Ehsan; Hoover, Amy; Koutis, Ioannis; Parviz, Ali (April 2022, Agent Learning in Open-Endedness (ALOE) Workshop. ICRL 2022)

   Ensemble learning, in its simplest form, entails the training of multiple models with the same training set. In a standard supervised setting, the training set can be viewed as a 'teacher' with an unbounded capacity of interactions with a single group of 'trainee' models. One can then ask the following broad question: How can we train an ensemble if the teacher has a bounded capacity of interactions with the trainees? Towards answering this question we consider how humans learn in peer groups. The problem of how to group individuals in order to maximize outcomes via cooperative learning has been debated for a long time by social scientists and policymakers. More recently, it has attracted research attention from an algorithmic standpoint which led to the design of grouping policies that appear to result in better aggregate learning in experiments with human subjects. Inspired by human peer learning, we hypothesize that using partially trained models as teachers to other less accurate models, i.e.~viewing ensemble learning as a peer process, can provide a solution to our central question. We further hypothesize that grouping policies, that match trainer models with learner models play a significant role in the overall learning outcome of the ensemble. We present a formalization and through extensive experiments with different types of classifiers, we demonstrate that: (i) an ensemble can reach surprising levels of performance with little interaction with the training set (ii) grouping policies definitely have an impact on the ensemble performance, in agreement with previous intuition and observations in human peer learning. 

   more » « less