Sam L. Polk
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sam L. Polk has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- James Michael Murphy
Department of Mathematics Tufts University 02155 Medford MA USA
3 shared publications - Bruce M. Boghosian
Tufts University
2 shared publications - Aland H. Y. Chan
Conservation Research Institute, University of Cambridge, Downing Street, Cambridge CB2 3EA, UK
1 shared publication Breanna R Ethridge
Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, United States of America
1 shared publication- Curran Schiefelbein
MIT Lincoln Laboratory, Lexington, Massachusetts, USA
1 shared publication - David Anthony Coomes
Department of Plant Sciences, University of Cambridge, Cambridge, UK
1 shared publication
Latest Publications
- Open Access
- 18 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Human-Robot Interaction
- Vol. 15 (1) , 1-18
Asynchronous Training of Mixed-Role Human Actors in a Partially Observable Environment
In cooperative training, humans within a team coordinate on complex tasks, building mental models of their teammates and learning to adapt to teammates’ actions in real-time. To reduce the often prohibitive scheduling constraints associated with cooperative training, this article introduces a paradigm for cooperative asynchronous training of human teams in which trainees practice coordination with autonomous teammates rather than humans. We introduce a novel experimental design for evaluating autonomous teammates for use as training partners in cooperative training. We apply this design to a human-subjects experiment where humans are trained with either another human or an autonomous teammate and are evaluated with a new human subject in a new, partially observable, cooperative game developed for this study. Importantly, we employ an unsupervised sequential clustering methodology to partition teammate trajectories from demonstrations performed in the experiment to form a smaller number of training conditions. This results in a simpler experiment design, enabling us to conduct a complex cooperative training human-subjects study in a reasonable amount of time. Through a demonstration of the proposed experimental design, we provide takeaways and design recommendations for future research in the development of cooperative asynchronous training systems utilizing robot surrogates for human teammates.
- 18 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Human-Robot Interaction
- Vol. 15 (1) , 1-18
Open AccessAsynchronous Training of Mixed-Role Human Actors in a Partially Observable Environment
In cooperative training, humans within a team coordinate on complex tasks, building mental models of their teammates and learning to adapt to teammates’ actions in real-time. To reduce the often prohibitive scheduling constraints associated with cooperative training, this article introduces a paradigm for cooperative asynchronous training of human teams in which trainees practice coordination with autonomous teammates rather than humans. We introduce a novel experimental design for evaluating autonomous teammates for use as training partners in cooperative training. We apply this design to a human-subjects experiment where humans are trained with either another human or an autonomous teammate and are evaluated with a new human subject in a new, partially observable, cooperative game developed for this study. Importantly, we employ an unsupervised sequential clustering methodology to partition teammate trajectories from demonstrations performed in the experiment to form a smaller number of training conditions. This results in a simpler experiment design, enabling us to conduct a complex cooperative training human-subjects study in a reasonable amount of time. Through a demonstration of the proposed experimental design, we provide takeaways and design recommendations for future research in the development of cooperative asynchronous training systems utilizing robot surrogates for human teammates.
- Open Access
- 15 February 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (4) , 1053
Unsupervised Diffusion and Volume Maximization-Based Clustering of Hyperspectral Images
Hyperspectral images taken from aircraft or satellites contain information from hundreds of spectral bands, within which lie latent lower-dimensional structures that can be exploited for classifying vegetation and other materials. A disadvantage of working with hyperspectral images is that, due to an inherent trade-off between spectral and spatial resolution, they have a relatively coarse spatial scale, meaning that single pixels may correspond to spatial regions containing multiple materials. This article introduces the Diffusion and Volume maximization-based Image Clustering (D-VIC) algorithm for unsupervised material clustering to address this problem. By directly incorporating pixel purity into its labeling procedure, D-VIC gives greater weight to pixels corresponding to a spatial region containing just a single material. D-VIC is shown to outperform comparable state-of-the-art methods in extensive experiments on a range of hyperspectral images, including land-use maps and highly mixed forest health surveys (in the context of ash dieback disease), implying that it is well-equipped for unsupervised material clustering of spectrally-mixed hyperspectral datasets.
- 15 February 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (4) , 1053
Open AccessUnsupervised Diffusion and Volume Maximization-Based Clustering of Hyperspectral Images
Hyperspectral images taken from aircraft or satellites contain information from hundreds of spectral bands, within which lie latent lower-dimensional structures that can be exploited for classifying vegetation and other materials. A disadvantage of working with hyperspectral images is that, due to an inherent trade-off between spectral and spatial resolution, they have a relatively coarse spatial scale, meaning that single pixels may correspond to spatial regions containing multiple materials. This article introduces the Diffusion and Volume maximization-based Image Clustering (D-VIC) algorithm for unsupervised material clustering to address this problem. By directly incorporating pixel purity into its labeling procedure, D-VIC gives greater weight to pixels corresponding to a spatial region containing just a single material. D-VIC is shown to outperform comparable state-of-the-art methods in extensive experiments on a range of hyperspectral images, including land-use maps and highly mixed forest health surveys (in the context of ash dieback disease), implying that it is well-equipped for unsupervised material clustering of spectrally-mixed hyperspectral datasets.
- Open Access
Multiscale Clustering of Hyperspectral Images Through Spectral-Spatial Diffusion Geometry
Clustering algorithms partition a dataset into groups of similar points. The primary contribution of this article is the Multiscale Spatially-Regularized Diffusion Learning (M-SRDL) clustering algorithm, which uses spatially-regularized diffusion distances to efficiently and accurately learn multiple scales of latent structure in hyperspectral images. The M-SRDL clustering algorithm extracts clusterings at many scales from a hyperspectral image and outputs these clusterings' variation of information-barycenter as an exemplar for all underlying cluster structure. We show that incorporating spatial regularization into a multiscale clustering framework results in smoother and more coherent clusters when applied to hyperspectral data, yielding more accurate clustering labels.
Open AccessMultiscale Clustering of Hyperspectral Images Through Spectral-Spatial Diffusion Geometry
Clustering algorithms partition a dataset into groups of similar points. The primary contribution of this article is the Multiscale Spatially-Regularized Diffusion Learning (M-SRDL) clustering algorithm, which uses spatially-regularized diffusion distances to efficiently and accurately learn multiple scales of latent structure in hyperspectral images. The M-SRDL clustering algorithm extracts clusterings at many scales from a hyperspectral image and outputs these clusterings' variation of information-barycenter as an exemplar for all underlying cluster structure. We show that incorporating spatial regularization into a multiscale clustering framework results in smoother and more coherent clusters when applied to hyperspectral data, yielding more accurate clustering labels.
- 1 March 2022
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 57, 58-100
A multiscale environment for learning by diffusion
- 1 March 2022
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 57, 58-100
A multiscale environment for learning by diffusion
- Open Access
The Nonuniversality of Wealth Distribution Tails Near Wealth Condensation Criticality
In this work, we modify the affine wealth model of wealth distributions to examine the effects of nonconstant redistribution on the very wealthy. Previous studies of this model, restricted to flat redistribution schemes, have demonstrated the presence of a phase transition to a partially wealth-condensed state, or "partial oligarchy," at the critical value of an order parameter. These studies have also indicated the presence of an exponential tail in wealth distribution precisely at criticality. Away from criticality, the tail was observed to be Gaussian. In this work, we generalize the flat redistribution within the affine wealth model to allow for an essentially arbitrary redistribution policy. We show that the exponential tail observed near criticality in prior work is, in fact, a special case of a much broader class of critical, slower-than-Gaussian decays that depend sensitively on the corresponding asymptotic behavior of the progressive redistribution model used. We thereby demonstrate that the functional form of the tail of the wealth distribution in a near-critical society is not universal in nature but rather entirely determined by the specifics of public policy decisions. This is significant because most major economies today are observed to be near-critical.
Open AccessThe Nonuniversality of Wealth Distribution Tails Near Wealth Condensation Criticality
In this work, we modify the affine wealth model of wealth distributions to examine the effects of nonconstant redistribution on the very wealthy. Previous studies of this model, restricted to flat redistribution schemes, have demonstrated the presence of a phase transition to a partially wealth-condensed state, or "partial oligarchy," at the critical value of an order parameter. These studies have also indicated the presence of an exponential tail in wealth distribution precisely at criticality. Away from criticality, the tail was observed to be Gaussian. In this work, we generalize the flat redistribution within the affine wealth model to allow for an essentially arbitrary redistribution policy. We show that the exponential tail observed near criticality in prior work is, in fact, a special case of a much broader class of critical, slower-than-Gaussian decays that depend sensitively on the corresponding asymptotic behavior of the progressive redistribution model used. We thereby demonstrate that the functional form of the tail of the wealth distribution in a near-critical society is not universal in nature but rather entirely determined by the specifics of public policy decisions. This is significant because most major economies today are observed to be near-critical.
- 1 January 2021
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Applied Mathematics
- Vol. 81 (4) , 1717-1741
The Nonuniversality of Wealth Distribution Tails Near Wealth Condensation Criticality
In this work, we modify the affine wealth model of wealth distributions to examine the effects of nonconstant redistribution on the very wealthy. Previous studies of this model, restricted to flat ...
- 1 January 2021
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Applied Mathematics
- Vol. 81 (4) , 1717-1741
The Nonuniversality of Wealth Distribution Tails Near Wealth Condensation Criticality
In this work, we modify the affine wealth model of wealth distributions to examine the effects of nonconstant redistribution on the very wealthy. Previous studies of this model, restricted to flat ...
- 29 July 2020
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 17 (4) , 046020
Improved tracking of sevoflurane anesthetic states with drug-specific machine learning models
Objective. The ability to monitor anesthetic states using automated approaches is expected to reduce inaccurate drug dosing and side-effects. Commercially available anesthetic state monitors perform poorly when ketamine is administered as an anesthetic-analgesic adjunct. Poor performance is likely because the models underlying these monitors are not optimized for the electroencephalogram (EEG) oscillations that are unique to the co-administration of ketamine. Approach. In this work, we designed two k -nearest neighbors algorithms for anesthetic state prediction. Main results. The first algorithm was trained only on sevoflurane EEG data, making it sevoflurane-specific. This algorithm enabled discrimination of the sevoflurane general anesthesia (GA) state from sedated and awake states (true positive rate = 0.87, [95% CI, 0.76, 0.97]). However, it did not enable discrimination of the sevoflurane- plus -ketamine GA state from sedated and awake states (true positive rate = 0.43, [0.19, 0.67]). In our second algorithm, we implemented a cross drug training paradigm by including both sevoflurane and sevoflurane- plus -ketamine EEG data in our training set. This algorithm enabled discrimination of the sevoflurane- plus -ketamine GA state from sedated and awake states (true positive rate = 0.91, [0.84, 0.98]). Significance. Instead of a one-algorithm-fits-all-drugs approach to anesthetic state monitoring, our results suggest that drug-specific models are necessary to improve the performance of automated anesthetic state monitors.
- 29 July 2020
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 17 (4) , 046020
Improved tracking of sevoflurane anesthetic states with drug-specific machine learning models
Objective. The ability to monitor anesthetic states using automated approaches is expected to reduce inaccurate drug dosing and side-effects. Commercially available anesthetic state monitors perform poorly when ketamine is administered as an anesthetic-analgesic adjunct. Poor performance is likely because the models underlying these monitors are not optimized for the electroencephalogram (EEG) oscillations that are unique to the co-administration of ketamine. Approach. In this work, we designed two k -nearest neighbors algorithms for anesthetic state prediction. Main results. The first algorithm was trained only on sevoflurane EEG data, making it sevoflurane-specific. This algorithm enabled discrimination of the sevoflurane general anesthesia (GA) state from sedated and awake states (true positive rate = 0.87, [95% CI, 0.76, 0.97]). However, it did not enable discrimination of the sevoflurane- plus -ketamine GA state from sedated and awake states (true positive rate = 0.43, [0.19, 0.67]). In our second algorithm, we implemented a cross drug training paradigm by including both sevoflurane and sevoflurane- plus -ketamine EEG data in our training set. This algorithm enabled discrimination of the sevoflurane- plus -ketamine GA state from sedated and awake states (true positive rate = 0.91, [0.84, 0.98]). Significance. Instead of a one-algorithm-fits-all-drugs approach to anesthetic state monitoring, our results suggest that drug-specific models are necessary to improve the performance of automated anesthetic state monitors.