Vasileios Charisopoulos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vasileios Charisopoulos has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Rebecca Willett
Univ. of Chicago, IL (United States)
4 shared publications - Anil Damle
Cornell University
3 shared publications - Austin R. Benson
Cornell University
3 shared publications - Jeremy Hoskins
Department of Statistics and Committee on Computational and Applied Mathematics University of Chicago Chicago IL USA
3 shared publications - Olivia Tsang3 shared publications
- Owen Melia
Section of Genetic Medicine, Department of Medicine, The University of Chicago, Chicago, IL, USA
3 shared publications
Latest Publications
- Open Access
- 30 September 2026
- Published by Elsevier in Journal of Computational Physics
- Vol. 569
A model-guided neural network method for the inverse scattering problem
- 30 September 2026
- Published by Elsevier in Journal of Computational Physics
- Vol. 569
Open AccessA model-guided neural network method for the inverse scattering problem
- Open Access
- 14 February 2026
- Published by Elsevier in SSRN Electronic Journal
A Model-Guided Neural Network Method for the Inverse Scattering Problem
Inverse medium scattering is an ill-posed, nonlinear wave-based imaging problem arising in medical imaging, remote sensing, and non-destructive testing. Machine learning (ML) methods offer increased inference speed and flexibility in capturing prior knowledge of imaging targets relative to classical optimization-based approaches; however, they perform poorly in regimes where the scattering behavior is highly nonlinear. A key limitation is that ML methods struggle to incorporate the physics governing the scattering process, which are typically inferred implicitly from the training data or loosely enforced via architectural design. In this paper, we present a method that endows a machine learning framework with explicit knowledge of problem physics, in the form of a differentiable solver representing the forward model. The proposed method progressively refines reconstructions of the scattering potential using measurements at increasing wave frequencies, following a classical strategy to stabilize recovery. Empirically, we find that our method provides high-quality reconstructions at a fraction of the computational or sampling costs of competing approaches.
- 14 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Model-Guided Neural Network Method for the Inverse Scattering Problem
Inverse medium scattering is an ill-posed, nonlinear wave-based imaging problem arising in medical imaging, remote sensing, and non-destructive testing. Machine learning (ML) methods offer increased inference speed and flexibility in capturing prior knowledge of imaging targets relative to classical optimization-based approaches; however, they perform poorly in regimes where the scattering behavior is highly nonlinear. A key limitation is that ML methods struggle to incorporate the physics governing the scattering process, which are typically inferred implicitly from the training data or loosely enforced via architectural design. In this paper, we present a method that endows a machine learning framework with explicit knowledge of problem physics, in the form of a differentiable solver representing the forward model. The proposed method progressively refines reconstructions of the scattering potential using measurements at increasing wave frequencies, following a classical strategy to stabilize recovery. Empirically, we find that our method provides high-quality reconstructions at a fraction of the computational or sampling costs of competing approaches.
- 13 May 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Mathematics of Data Science
- Vol. 7 (2) , 699-722
Nonlinear Tomographic Reconstruction via Nonsmooth Optimization
We study iterative signal reconstruction in computed tomography, wherein measurements are produced by a linear transformation of the unknown signal followed by an exponential nonlinear map. Approaches based on preprocessing the data with a log transform and then solving the resulting linear inverse problem are tempting since they are amenable to convex optimization methods; however, such methods perform poorly when the underlying image has high dynamic range, as in X-ray imaging of tissue with embedded metal. We show that a suitably initialized subgradient method applied to a natural nonsmooth, nonconvex loss function produces iterates that converge to the unknown signal of interest at a geometric rate under the statistical model proposed by Fridovich-Keil et al. [ Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction, 2023]. Our recovery program enjoys improved conditioning compared to the formulation proposed by the latter work, enabling faster iterative reconstruction from substantially fewer samples.
- 13 May 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Mathematics of Data Science
- Vol. 7 (2) , 699-722
Nonlinear Tomographic Reconstruction via Nonsmooth Optimization
We study iterative signal reconstruction in computed tomography, wherein measurements are produced by a linear transformation of the unknown signal followed by an exponential nonlinear map. Approaches based on preprocessing the data with a log transform and then solving the resulting linear inverse problem are tempting since they are amenable to convex optimization methods; however, such methods perform poorly when the underlying image has high dynamic range, as in X-ray imaging of tissue with embedded metal. We show that a suitably initialized subgradient method applied to a natural nonsmooth, nonconvex loss function produces iterates that converge to the unknown signal of interest at a geometric rate under the statistical model proposed by Fridovich-Keil et al. [ Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction, 2023]. Our recovery program enjoys improved conditioning compared to the formulation proposed by the latter work, enabling faster iterative reconstruction from substantially fewer samples.
- Open Access
- 3 February 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 527
Multi-frequency progressive refinement for learned inverse scattering
- 3 February 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 527
Open AccessMulti-frequency progressive refinement for learned inverse scattering
- 1 August 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Mathematics of Operations Research
- Vol. 49 (3) , 1678-1709
A Superlinearly Convergent Subgradient Method for Sharp Semismooth Problems
Subgradient methods comprise a fundamental class of nonsmooth optimization algorithms. Classical results show that certain subgradient methods converge sublinearly for general Lipschitz convex functions and converge linearly for convex functions that grow sharply away from solutions. Recent work has moreover extended these results to certain nonconvex problems. In this work, we seek to improve the complexity of these algorithms by asking the following question. Is it possible to design a superlinearly convergent subgradient method? We provide a positive answer to this question for a broad class of sharp semismooth functions. Funding: The research of D. Davis was supported by the Division of Mathematical Sciences [Grant 2047637] and the Alfred P. Sloan Foundation.
- 1 August 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Mathematics of Operations Research
- Vol. 49 (3) , 1678-1709
A Superlinearly Convergent Subgradient Method for Sharp Semismooth Problems
Subgradient methods comprise a fundamental class of nonsmooth optimization algorithms. Classical results show that certain subgradient methods converge sublinearly for general Lipschitz convex functions and converge linearly for convex functions that grow sharply away from solutions. Recent work has moreover extended these results to certain nonconvex problems. In this work, we seek to improve the complexity of these algorithms by asking the following question. Is it possible to design a superlinearly convergent subgradient method? We provide a positive answer to this question for a broad class of sharp semismooth functions. Funding: The research of D. Davis was supported by the Division of Mathematical Sciences [Grant 2047637] and the Alfred P. Sloan Foundation.
- Open Access
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 47, 6588-6595
Reducing Aggregate Electric Vehicle Battery Capacity Through Sharing
Meeting demand for automotive battery resources is predicted to be costly from both economic and environmental perspectives. To minimize costs, battery resources should be deployed as efficiently as possible. A potential source of inefficiency in battery deployment is that the batteries of personal vehicles are typically much larger than necessary to meet most daily mobility needs. In this paper, we consider whether battery resources can be used more efficiently in a setting where drivers, in addition to having personal vehicle batteries, have access to a shared battery resource. More precisely, we consider the problem of minimizing aggregate battery capacity in settings with and without a shared resource subject to the requirement that driver commuting needs are met with high reliability. To assess capacity reduction potential, we quantify the difference in deployed battery capacity in settings with and without a shared resource in a case study using real-world longitudinal mobility data from Puget Sound, Washington. We find that access to a shared battery resource can substantially reduce deployed battery capacity. Furthermore, relative reductions in battery capacity increase with number of drivers and the level of reliability desired.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 47, 6588-6595
Open AccessReducing Aggregate Electric Vehicle Battery Capacity Through Sharing
Meeting demand for automotive battery resources is predicted to be costly from both economic and environmental perspectives. To minimize costs, battery resources should be deployed as efficiently as possible. A potential source of inefficiency in battery deployment is that the batteries of personal vehicles are typically much larger than necessary to meet most daily mobility needs. In this paper, we consider whether battery resources can be used more efficiently in a setting where drivers, in addition to having personal vehicle batteries, have access to a shared battery resource. More precisely, we consider the problem of minimizing aggregate battery capacity in settings with and without a shared resource subject to the requirement that driver commuting needs are met with high reliability. To assess capacity reduction potential, we quantify the difference in deployed battery capacity in settings with and without a shared resource in a case study using real-world longitudinal mobility data from Puget Sound, Washington. We find that access to a shared battery resource can substantially reduce deployed battery capacity. Furthermore, relative reductions in battery capacity increase with number of drivers and the level of reliability desired.
- Open Access
Robust and differentially private stochastic linear bandits
In this paper, we study the stochastic linear bandit problem under the additional requirements of differential privacy, robustness and batched observations. In particular, we assume an adversary randomly chooses a constant fraction of the observed rewards in each batch, replacing them with arbitrary numbers. We present differentially private and robust variants of the arm elimination algorithm using logarithmic batch queries under two privacy models and provide regret bounds in both settings. In the first model, every reward in each round is reported by a potentially different client, which reduces to standard local differential privacy (LDP). In the second model, every action is "owned" by a different client, who may aggregate the rewards over multiple queries and privatize the aggregate response instead. To the best of our knowledge, our algorithms are the first simultaneously providing differential privacy and adversarial robustness in the stochastic linear bandits problem.
Open AccessRobust and differentially private stochastic linear bandits
In this paper, we study the stochastic linear bandit problem under the additional requirements of differential privacy, robustness and batched observations. In particular, we assume an adversary randomly chooses a constant fraction of the observed rewards in each batch, replacing them with arbitrary numbers. We present differentially private and robust variants of the arm elimination algorithm using logarithmic batch queries under two privacy models and provide regret bounds in both settings. In the first model, every reward in each round is reported by a potentially different client, which reduces to standard local differential privacy (LDP). In the second model, every action is "owned" by a different client, who may aggregate the rewards over multiple queries and privatize the aggregate response instead. To the best of our knowledge, our algorithms are the first simultaneously providing differential privacy and adversarial robustness in the stochastic linear bandits problem.
- Open Access
Reducing Aggregate Electric Vehicle Battery Capacity through Sharing
Meeting growing demand for automotive battery resources is predicted to be costly from both economic and environmental perspectives. To minimize these costs, battery resources should be deployed as efficiently as possible. A potential source of inefficiency in battery deployment is the fact that the batteries of personal vehicles are typically much larger than needed to meet most daily mobility needs. In this paper, we consider whether battery resources can be used more efficiently in a setting where drivers, in addition to having personal vehicle batteries, have access to a shared battery resource. More precisely, we consider the problem of minimizing aggregate battery capacity in settings with and without a shared resource subject to the requirement that driver commuting needs are met with high reliability. To assess the potential for reductions in deployed battery capacity with the addition of a shared resource, we quantify the difference in deployed battery capacity with and without a shared resource in case study using real-world longitudinal mobility data from Puget Sound, Washington. We find that giving drivers access to a shared battery resource can substantially reduces deployed battery capacity. Furthermore, relative reductions in battery capacity increase with number of drivers and the level of reliability desired.
Open AccessReducing Aggregate Electric Vehicle Battery Capacity through Sharing
Meeting growing demand for automotive battery resources is predicted to be costly from both economic and environmental perspectives. To minimize these costs, battery resources should be deployed as efficiently as possible. A potential source of inefficiency in battery deployment is the fact that the batteries of personal vehicles are typically much larger than needed to meet most daily mobility needs. In this paper, we consider whether battery resources can be used more efficiently in a setting where drivers, in addition to having personal vehicle batteries, have access to a shared battery resource. More precisely, we consider the problem of minimizing aggregate battery capacity in settings with and without a shared resource subject to the requirement that driver commuting needs are met with high reliability. To assess the potential for reductions in deployed battery capacity with the addition of a shared resource, we quantify the difference in deployed battery capacity with and without a shared resource in case study using real-world longitudinal mobility data from Puget Sound, Washington. We find that giving drivers access to a shared battery resource can substantially reduces deployed battery capacity. Furthermore, relative reductions in battery capacity increase with number of drivers and the level of reliability desired.
- Open Access
Communication-efficient distributed eigenspace estimation
Distributed computing is a standard way to scale up machine learning and data science algorithms to process large amounts of data. In such settings, avoiding communication amongst machines is paramount for achieving high performance. Rather than distribute the computation of existing algorithms, a common practice for avoiding communication is to compute local solutions or parameter estimates on each machine and then combine the results; in many convex optimization problems, even simple averaging of local solutions can work well. However, these schemes do not work when the local solutions are not unique. Spectral methods are a collection of such problems, where solutions are orthonormal bases of the leading invariant subspace of an associated data matrix, which are only unique up to rotation and reflections. Here, we develop a communication-efficient distributed algorithm for computing the leading invariant subspace of a data matrix. Our algorithm uses a novel alignment scheme that minimizes the Procrustean distance between local solutions and a reference solution, and only requires a single round of communication. For the important case of principal component analysis (PCA), we show that our algorithm achieves a similar error rate to that of a centralized estimator. We present numerical experiments demonstrating the efficacy of our proposed algorithm for distributed PCA, as well as other problems where solutions exhibit rotational symmetry, such as node embeddings for graph data and spectral initialization for quadratic sensing.
Open AccessCommunication-efficient distributed eigenspace estimation
Distributed computing is a standard way to scale up machine learning and data science algorithms to process large amounts of data. In such settings, avoiding communication amongst machines is paramount for achieving high performance. Rather than distribute the computation of existing algorithms, a common practice for avoiding communication is to compute local solutions or parameter estimates on each machine and then combine the results; in many convex optimization problems, even simple averaging of local solutions can work well. However, these schemes do not work when the local solutions are not unique. Spectral methods are a collection of such problems, where solutions are orthonormal bases of the leading invariant subspace of an associated data matrix, which are only unique up to rotation and reflections. Here, we develop a communication-efficient distributed algorithm for computing the leading invariant subspace of a data matrix. Our algorithm uses a novel alignment scheme that minimizes the Procrustean distance between local solutions and a reference solution, and only requires a single round of communication. For the important case of principal component analysis (PCA), we show that our algorithm achieves a similar error rate to that of a centralized estimator. We present numerical experiments demonstrating the efficacy of our proposed algorithm for distributed PCA, as well as other problems where solutions exhibit rotational symmetry, such as node embeddings for graph data and spectral initialization for quadratic sensing.
- Top Cited PapersOpen Access
- 2 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 109 (5) , 728-755
Tropical Geometry and Machine Learning
Tropical geometry is a relatively recent field in mathematics and computer science, combining elements of algebraic geometry and polyhedral geometry. The scalar arithmetic of its analytic part preexisted in the form of max-plus and min-plus semiring arithmetic used in finite automata, nonlinear image processing, convex analysis, nonlinear control, optimization, and idempotent mathematics. Tropical geometry recently emerged in the analysis and extension of several classes of problems and systems in both classical machine learning and deep learning. Three such areas include: 1) deep neural networks with piecewise linear (PWL) activation functions; 2) probabilistic graphical models; and 3) nonlinear regression with PWL functions. In this article, we first summarize introductory ideas and objects of tropical geometry, providing a theoretical framework for both the max-plus algebra that underlies tropical geometry and its extensions to general max algebras. This unifies scalar and vector/signal operations over a class of nonlinear spaces, called weighted lattices, and allows us to provide optimal solutions for algebraic equations used in tropical geometry and generalize tropical geometric objects. Then, we survey the state of the art and recent progress in the aforementioned areas. First, we illustrate a purely geometric approach for studying the representation power of neural networks with PWL activations. Then, we review the tropical geometric analysis of parametric statistical models, such as HMMs; later, we focus on the Viterbi algorithm and related methods for weighted finite-state transducers and provide compact and elegant representations via their formal tropical modeling. Finally, we provide optimal solutions and an efficient algorithm for the convex regression problem, using concepts and tools from tropical geometry and max-plus algebra. Throughout this article, we also outline problems and future directions in machine learning that can benefit from the tropical-geometric point of view.
- 2 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 109 (5) , 728-755
Top Cited PapersOpen AccessTropical Geometry and Machine Learning
Tropical geometry is a relatively recent field in mathematics and computer science, combining elements of algebraic geometry and polyhedral geometry. The scalar arithmetic of its analytic part preexisted in the form of max-plus and min-plus semiring arithmetic used in finite automata, nonlinear image processing, convex analysis, nonlinear control, optimization, and idempotent mathematics. Tropical geometry recently emerged in the analysis and extension of several classes of problems and systems in both classical machine learning and deep learning. Three such areas include: 1) deep neural networks with piecewise linear (PWL) activation functions; 2) probabilistic graphical models; and 3) nonlinear regression with PWL functions. In this article, we first summarize introductory ideas and objects of tropical geometry, providing a theoretical framework for both the max-plus algebra that underlies tropical geometry and its extensions to general max algebras. This unifies scalar and vector/signal operations over a class of nonlinear spaces, called weighted lattices, and allows us to provide optimal solutions for algebraic equations used in tropical geometry and generalize tropical geometric objects. Then, we survey the state of the art and recent progress in the aforementioned areas. First, we illustrate a purely geometric approach for studying the representation power of neural networks with PWL activations. Then, we review the tropical geometric analysis of parametric statistical models, such as HMMs; later, we focus on the Viterbi algorithm and related methods for weighted finite-state transducers and provide compact and elegant representations via their formal tropical modeling. Finally, we provide optimal solutions and an efficient algorithm for the convex regression problem, using concepts and tools from tropical geometry and max-plus algebra. Throughout this article, we also outline problems and future directions in machine learning that can benefit from the tropical-geometric point of view.