Daniel D. Lee
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
Daniel D. Lee has a total of 158 co-authors. Here are the top co-authors by number of shared publications:
Paul Vernaza
GRASP Lab, University of Pennsylvania, 3330 Walnut St., Philadelphia, 19104, USA
7 shared publicationsYuanqing Lin
5 shared publicationsAlex Kushleyev
Graduate School of Engineering , Tohoku University , 6-6-01, Aramaki-Aoba, Aoba-ku , Sendai , 980-8579 , Japan
3 shared publicationsDennis Hong
University of California at Los Angeles
3 shared publications- Dennis Hong
Robotics and Mechanisms Laboratory, Department of Mechanical and Aerospace Engineering, University of California, Los Angeles, CA, USA
3 shared publications Jihun Ham
University of Pennsylvania
3 shared publications
Latest Publications
- Open Access
- 5 October 2026
- Published by American Physical Society (APS) in Physical Review Research
- Vol. 8 (4)
Hierarchy of collective ordering in swarmalator systems
We introduce an exactly solvable multispecies spherical spin model that unifies noisy Kuramoto dynamics and equilibrium swarmalator systems within a single mean-field framework. The hierarchy of collective ordering in swarmalator systems is elucidated by analytically mapping the full three-dimensional phase diagram, classifying the various collective phases, and determining their corresponding first- and second-order transition boundaries. Our results reveal that the diverse states of swarmalator systems are driven by the competition and cooperation between internal and cross-species couplings. This establishes the spherical spin model as a mathematically tractable foundation for understanding collective behavior in active phase systems and their higher-dimensional generalizations.
- 5 October 2026
- Published by American Physical Society (APS) in Physical Review Research
- Vol. 8 (4)
Open AccessHierarchy of collective ordering in swarmalator systems
We introduce an exactly solvable multispecies spherical spin model that unifies noisy Kuramoto dynamics and equilibrium swarmalator systems within a single mean-field framework. The hierarchy of collective ordering in swarmalator systems is elucidated by analytically mapping the full three-dimensional phase diagram, classifying the various collective phases, and determining their corresponding first- and second-order transition boundaries. Our results reveal that the diverse states of swarmalator systems are driven by the competition and cooperation between internal and cross-species couplings. This establishes the spherical spin model as a mathematically tractable foundation for understanding collective behavior in active phase systems and their higher-dimensional generalizations.
- Open Access
- 23 September 2026
- Published by Elsevier in SSRN Electronic Journal
Uncovering Sex Differences in the Drosophila VentralNerve Cord Through Connectome Alignment
There are now multiple Drosophila connectomes available, spanning the brain and nerve cord. Comparing these connectomes requires first classifying neurons into cell types, a process that requires extensive manual curation. Here we introduce a new method that automatically aligns connectomes using network topology alone. Leveraging two complete male Drosophila ventral nerve cords previously cell-typed via painstaking manual and semi-automated approaches, we automatically assign cell types to the ~13,000 intrinsic neurons of a female nerve cord and identify sex-specific and sexually dimorphic cell types. To demonstrate the utility of the predicted sex differences, we focus on circuits underlying song production in males and oviposition behaviors in females. By doing so, we uncover a variety of circuits involved in sex-specific behaviors. Our analyses provide insights into sex differences in circuits that connect the brain and body, and pave the way for the rapid automated cell typing required for comparative connectomics at scale.
- 23 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessUncovering Sex Differences in the Drosophila VentralNerve Cord Through Connectome Alignment
There are now multiple Drosophila connectomes available, spanning the brain and nerve cord. Comparing these connectomes requires first classifying neurons into cell types, a process that requires extensive manual curation. Here we introduce a new method that automatically aligns connectomes using network topology alone. Leveraging two complete male Drosophila ventral nerve cords previously cell-typed via painstaking manual and semi-automated approaches, we automatically assign cell types to the ~13,000 intrinsic neurons of a female nerve cord and identify sex-specific and sexually dimorphic cell types. To demonstrate the utility of the predicted sex differences, we focus on circuits underlying song production in males and oviposition behaviors in females. By doing so, we uncover a variety of circuits involved in sex-specific behaviors. Our analyses provide insights into sex differences in circuits that connect the brain and body, and pave the way for the rapid automated cell typing required for comparative connectomics at scale.
- Open Access
- 1 July 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-15
Parametric matrix models
We present a general class of machine learning algorithms called parametric matrix models. In contrast with most existing machine learning models that imitate the biology of neurons, parametric matrix models use matrix equations that emulate physical systems. Similar to how physics problems are usually solved, parametric matrix models learn the governing equations that lead to the desired outputs. Parametric matrix models can be efficiently trained from empirical data, and the equations may use algebraic, differential, or integral relations. While originally designed for scientific computing, we prove that parametric matrix models are universal function approximators that can be applied to general machine learning problems. After introducing the underlying theory, we apply parametric matrix models to a series of different challenges that show their performance for a wide range of problems. For all the challenges tested here, parametric matrix models produce accurate results within an efficient and interpretable computational framework that allows for input feature extrapolation.
- 1 July 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-15
Open AccessParametric matrix models
We present a general class of machine learning algorithms called parametric matrix models. In contrast with most existing machine learning models that imitate the biology of neurons, parametric matrix models use matrix equations that emulate physical systems. Similar to how physics problems are usually solved, parametric matrix models learn the governing equations that lead to the desired outputs. Parametric matrix models can be efficiently trained from empirical data, and the equations may use algebraic, differential, or integral relations. While originally designed for scientific computing, we prove that parametric matrix models are universal function approximators that can be applied to general machine learning problems. After introducing the underlying theory, we apply parametric matrix models to a series of different challenges that show their performance for a wide range of problems. For all the challenges tested here, parametric matrix models produce accurate results within an efficient and interpretable computational framework that allows for input feature extrapolation.
- 4 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 8737-8744
EV-Catcher: High-Speed Object Catching Using Low-Latency Event-Based Neural Networks
Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to standard CMOS-based imagers. These properties make them ideal tools for real-time perception tasks in highly dynamic environments. In this work, we demonstrate an application where event cameras excel: accurately estimating the impact location of fast-moving objects. We introduce a lightweight event representation called Binary Event History Image (BEHI) to encode event data at low latency, as well as a learning-based approach that allows real-time inference of a confidence-enabled control signal to the robot. To validate our approach, we present an experimental catching system in which we catch fast-flying ping-pong balls. We show that the system is capable of achieving a success rate of 81% in catching balls targeted at different locations, with a velocity of up to$13\,\text{m/s}$ even on compute-constrained embedded platforms such as the Nvidia Jetson NX.- 4 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 8737-8744
EV-Catcher: High-Speed Object Catching Using Low-Latency Event-Based Neural Networks
Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to standard CMOS-based imagers. These properties make them ideal tools for real-time perception tasks in highly dynamic environments. In this work, we demonstrate an application where event cameras excel: accurately estimating the impact location of fast-moving objects. We introduce a lightweight event representation called Binary Event History Image (BEHI) to encode event data at low latency, as well as a learning-based approach that allows real-time inference of a confidence-enabled control signal to the robot. To validate our approach, we present an experimental catching system in which we catch fast-flying ping-pong balls. We show that the system is capable of achieving a success rate of 81% in catching balls targeted at different locations, with a velocity of up to$13\,\text{m/s}$ even on compute-constrained embedded platforms such as the Nvidia Jetson NX.- 1 July 2018
- Published by MIT Press in Neural Computation
- Vol. 30 (7) , 1930-1960
Bias Reduction and Metric Learning for Nearest-Neighbor Estimation of Kullback-Leibler Divergence
Nearest-neighbor estimators for the Kullback-Leiber (KL) divergence that are asymptotically unbiased have recently been proposed and demonstrated in a number of applications. However, with a small number of samples, nonparametric methods typically suffer from large estimation bias due to the nonlocality of information derived from nearest-neighbor statistics. In this letter, we show that this estimation bias can be mitigated by modifying the metric function, and we propose a novel method for learning a locally optimal Mahalanobis distance function from parametric generative models of the underlying density distributions. Using both simulations and experiments on a variety of data sets, we demonstrate that this interplay between approximate generative models and nonparametric techniques can significantly improve the accuracy of nearest-neighbor-based estimation of the KL divergence.
- 1 July 2018
- Published by MIT Press in Neural Computation
- Vol. 30 (7) , 1930-1960
Bias Reduction and Metric Learning for Nearest-Neighbor Estimation of Kullback-Leibler Divergence
Nearest-neighbor estimators for the Kullback-Leiber (KL) divergence that are asymptotically unbiased have recently been proposed and demonstrated in a number of applications. However, with a small number of samples, nonparametric methods typically suffer from large estimation bias due to the nonlocality of information derived from nearest-neighbor statistics. In this letter, we show that this estimation bias can be mitigated by modifying the metric function, and we propose a novel method for learning a locally optimal Mahalanobis distance function from parametric generative models of the underlying density distributions. Using both simulations and experiments on a variety of data sets, we demonstrate that this interplay between approximate generative models and nonparametric techniques can significantly improve the accuracy of nearest-neighbor-based estimation of the KL divergence.
- 10 April 2018
- Published by Springer Nature
- p. 381-427
Team THOR’s Entry in the DARPA Robotics Challenge Finals 2015
- 10 April 2018
- Published by Springer Nature
- p. 381-427
Team THOR’s Entry in the DARPA Robotics Challenge Finals 2015
- Open Access
Learning Data Manifolds with a Cutting Plane Method
We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom. Conventional data augmentation methods rely upon sampling large numbers of training examples from these manifolds; instead, we propose an iterative algorithm called M_{CP} based upon a cutting-plane approach that efficiently solves a quadratic semi-infinite programming problem to find the maximum margin solution. We provide a proof of convergence as well as a polynomial bound on the number of iterations required for a desired tolerance in the objective function. The efficiency and performance of M_{CP} are demonstrated in high-dimensional simulations and on image manifolds generated from the ImageNet dataset. Our results indicate that M_{CP} is able to rapidly learn good classifiers and shows superior generalization performance compared with conventional maximum margin methods using data augmentation methods.
Open AccessLearning Data Manifolds with a Cutting Plane Method
We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom. Conventional data augmentation methods rely upon sampling large numbers of training examples from these manifolds; instead, we propose an iterative algorithm called M_{CP} based upon a cutting-plane approach that efficiently solves a quadratic semi-infinite programming problem to find the maximum margin solution. We provide a proof of convergence as well as a polynomial bound on the number of iterations required for a desired tolerance in the objective function. The efficiency and performance of M_{CP} are demonstrated in high-dimensional simulations and on image manifolds generated from the ImageNet dataset. Our results indicate that M_{CP} is able to rapidly learn good classifiers and shows superior generalization performance compared with conventional maximum margin methods using data augmentation methods.
- Open Access
Maximizing Influence in an Ising Network: A Mean-Field Optimal Solution
Influence maximization in social networks has typically been studied in the context of contagion models and irreversible processes. In this paper, we consider an alternate model that treats individual opinions as spins in an Ising system at dynamic equilibrium. We formalize the \textit{Ising influence maximization} problem, which has a natural physical interpretation as maximizing the magnetization given a budget of external magnetic field. Under the mean-field (MF) approximation, we present a gradient ascent algorithm that uses the susceptibility to efficiently calculate local maxima of the magnetization, and we develop a number of sufficient conditions for when the MF magnetization is concave and our algorithm converges to a global optimum. We apply our algorithm on random and real-world networks, demonstrating, remarkably, that the MF optimal external fields (i.e., the external fields which maximize the MF magnetization) shift from focusing on high-degree individuals at high temperatures to focusing on low-degree individuals at low temperatures. We also establish a number of novel results about the structure of steady-states in the ferromagnetic MF Ising model on general graph topologies, which are of independent interest.
Open AccessMaximizing Influence in an Ising Network: A Mean-Field Optimal Solution
Influence maximization in social networks has typically been studied in the context of contagion models and irreversible processes. In this paper, we consider an alternate model that treats individual opinions as spins in an Ising system at dynamic equilibrium. We formalize the \textit{Ising influence maximization} problem, which has a natural physical interpretation as maximizing the magnetization given a budget of external magnetic field. Under the mean-field (MF) approximation, we present a gradient ascent algorithm that uses the susceptibility to efficiently calculate local maxima of the magnetization, and we develop a number of sufficient conditions for when the MF magnetization is concave and our algorithm converges to a global optimum. We apply our algorithm on random and real-world networks, demonstrating, remarkably, that the MF optimal external fields (i.e., the external fields which maximize the MF magnetization) shift from focusing on high-degree individuals at high temperatures to focusing on low-degree individuals at low temperatures. We also establish a number of novel results about the structure of steady-states in the ferromagnetic MF Ising model on general graph topologies, which are of independent interest.
- Open Access
- 8 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 40 (1) , 106-118
Generative Local Metric Learning for Nearest Neighbor Classification
We consider the problem of learning a local metric in order to enhance the performance of nearest neighbor classification. Conventional metric learning methods attempt to separate data distributions in a purely discriminative manner; here we show how to take advantage of information from parametric generative models. We focus on the bias in the information-theoretic error arising from finite sampling effects, and find an appropriate local metric that maximally reduces the bias based upon knowledge from generative models. As a byproduct, the asymptotic theoretical analysis in this work relates metric learning to dimensionality reduction from a novel perspective, which was not understood from previous discriminative approaches. Empirical experiments show that this learned local metric enhances the discriminative nearest neighbor performance on various datasets using simple class conditional generative models such as a Gaussian.
- 8 February 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 40 (1) , 106-118
Open AccessGenerative Local Metric Learning for Nearest Neighbor Classification
We consider the problem of learning a local metric in order to enhance the performance of nearest neighbor classification. Conventional metric learning methods attempt to separate data distributions in a purely discriminative manner; here we show how to take advantage of information from parametric generative models. We focus on the bias in the information-theoretic error arising from finite sampling effects, and find an appropriate local metric that maximally reduces the bias based upon knowledge from generative models. As a byproduct, the asymptotic theoretical analysis in this work relates metric learning to dimensionality reduction from a novel perspective, which was not understood from previous discriminative approaches. Empirical experiments show that this learned local metric enhances the discriminative nearest neighbor performance on various datasets using simple class conditional generative models such as a Gaussian.
- 26 December 2016
- Published by Wiley in Journal of Field Robotics
- Vol. 34 (4) , 775-801
Team THOR's Entry in the DARPA Robotics Challenge Finals 2015
- 26 December 2016
- Published by Wiley in Journal of Field Robotics
- Vol. 34 (4) , 775-801
Team THOR's Entry in the DARPA Robotics Challenge Finals 2015