71 citations · 151 across the 51 of their papers we have counts for
57 papers
Optimal Control in Hilbert Complex Spaces with Finite Element Exterior Calculus
Farid Bozorgnia, Michael Holst, Anshu Kumar +3
We develop a framework for PDE-constrained optimal control on Hilbert complexes and its structure-preserving discretization by finite element exterior calculus (FEEC), with emphasi…
Numerical Algorithms for Partially Segregated Elliptic Systems
Farid Bozorgnia, Avetik Arakelyan, Vyacheslav Kungurtsev +1
We develop numerical methods for elliptic systems governed by a ternary partial-segregation constraint, in which three nonnegative components are required to have a vanishing point…
Direct-search methods for decentralized blackbox optimization
El Houcine Bergou, Youssef Diouane, Vyacheslav Kungurtsev +1
Derivative-free optimization algorithms are particularly useful for tackling blackbox optimization problems where the objective function arises from complex and expensive procedure…
Quantum Solutions to the Privacy vs. Utility Tradeoff
Sagnik Chatterjee, Vyacheslav Kungurtsev
In this work, we propose a novel architecture (and several variants thereof) based on quantum cryptographic primitives with provable privacy and security guarantees regarding membe…
Inexact Direct-Search Methods for Bilevel Optimization Problems
Youssef Diouane, Vyacheslav Kungurtsev, Francesco Rinaldi +1
In this work, we introduce new direct search schemes for the solution of bilevel optimization (BO) problems. Our methods rely on a fixed accuracy black box oracle for the lower-lev…
Stochastic Approximation for Expectation Objective and Expectation Inequality-Constrained Nonconvex Optimization
Francisco Facchinei, Vyacheslav Kungurtsev
Stochastic Approximation has been a prominent set of tools for solving problems with noise and uncertainty. Increasingly, it becomes important to solve optimization problems wherei…
Hybrid Methods in Polynomial Optimisation
Johannes Aspman, Gilles Bareilles, Vyacheslav Kungurtsev +2
The Moment/Sum-of-squares hierarchy provides a way to compute the global minimizers of polynomial optimization problems (POP), at the cost of solving a sequence of increasingly lar…
A Stochastic-Gradient-based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems
Frank E. Curtis, Vyacheslav Kungurtsev, Daniel P. Robinson +1
A stochastic-gradient-based interior-point algorithm for minimizing a continuously differentiable objective function (that may be nonconvex) subject to bound constraints is present…
A Survey of Quantum Alternatives to Randomized Algorithms: Monte Carlo Integration and Beyond
Philip Intallura, Georgios Korpas, Sudeepto Chakraborty +4
Monte Carlo sampling is a powerful toolbox of algorithmic techniques widely used for a number of applications wherein some noisy quantity, or summary statistic thereof, is sought t…
A Sequential Quadratic Programming Method for Optimization with Stochastic Objective Functions, Deterministic Inequality Constraints and Robust Subproblems
Songqiang Qiu, Vyacheslav Kungurtsev
In this paper, a robust sequential quadratic programming method for constrained optimization is generalized to problem with an {expectation} objective function {and} deterministic…
Tame Riemannian Stochastic Approximation
Johannes Aspman, Vyacheslav Kungurtsev, Reza Roohi Seraji
We study the properties of stochastic approximation applied to a tame nondifferentiable function subject to constraints defined by a Riemannian manifold. The objective landscape of…
When Do Curricula Work in Federated Learning?
Saeed Vahidian, Sreevatsank Kadaveru, Woonjoon Baek +5
An oft-cited open problem of federated learning is the existence of data heterogeneity at the clients. One pathway to understanding the drastic accuracy drop in federated learning…
A Note on Optimal Tokamak Control for Fusion Power Simulation
M. Holst, V. Kungurtsev, S. Mukherjee
The Tokamak device is the most promising candidate for producing sustainable electric power by nuclear fusion. It is a torus-shaped device that confines plasma by a strong magnetic…
Jump-Diffusion Langevin Dynamics for Multimodal Posterior Sampling
Jacopo Guidolin, Vyacheslav Kungurtsev, Ondřej Kuželka
Bayesian methods of sampling from a posterior distribution are becoming increasingly popular due to their ability to precisely display the uncertainty of a model fit. Classical met…
Time-Varying Multi-Objective Optimization: Tradeoff Regret Bounds
Allahkaram Shafiei, Jakub Marecek
Multi-objective optimization studies the process of seeking multiple competing desiderata in some operation. Solution techniques highlight marginal tradeoffs associated with weighi…
Time-Varying Semidefinite Programming: Path Following a Burer-Monteiro Factorization
Antonio Bellon, Mareike Dressler, Vyacheslav Kungurtsev +2
We present an online algorithm for time-varying semidefinite programs (TV-SDPs), based on the tracking of the solution trajectory of a low-rank matrix factorization, also known as…
Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
Diyuan Wu, Vyacheslav Kungurtsev, Marco Mondelli
The stochastic heavy ball method (SHB), also known as stochastic gradient descent (SGD) with Polyak's momentum, is widely used in training neural networks. However, despite the rem…
Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces
Saeed Vahidian, Mahdi Morafah, Weijia Wang +4
Clustered federated learning (FL) has been shown to produce promising results by grouping clients into clusters. This is especially effective in scenarios where separate groups of…
Iteration Complexity of Variational Quantum Algorithms
Vyacheslav Kungurtsev, Georgios Korpas, Jakub Marecek +1
There has been much recent interest in near-term applications of quantum computers, i.e., using quantum circuits that have short decoherence times due to hardware limitations. Vari…
Stochastic Langevin Differential Inclusions with Applications to Machine Learning
Fabio V. Difonzo, Vyacheslav Kungurtsev, Jakub Marecek
Stochastic differential equations of Langevin-diffusion form have received significant attention, thanks to their foundational role in both Bayesian sampling algorithms and optimiz…
Scaling the Wild: Decentralizing Hogwild!-style Shared-memory SGD
Bapi Chatterjee, Vyacheslav Kungurtsev, Dan Alistarh
Powered by the simplicity of lock-free asynchrony, Hogwilld! is a go-to approach to parallelize SGD over a shared-memory setting. Despite its popularity and concomitant extensions,…
Retraction based Direct Search Methods for Derivative Free Riemannian Optimization
Vyacheslav Kungurtsev, Francesco Rinaldi, Damiano Zeffiro
Direct search methods represent a robust and reliable class of algorithms for solving black-box optimization problems. In this paper, we explore the application of those strategies…
Stochastic Model Predictive Control, Iterated Function Systems, and Stability
Vyacheslav Kungurtsev, Jakub Marecek, Robert Shorten
We present the observation that the process of stochastic model predictive control can be formulated in the framework of iterated function systems. The latter has a rich ergodic th…
On the Ergodic Control of Ensembles in the Presence of Non-linear Filters
Vyacheslav Kungurtsev, Jakub Marecek, Ramen Ghosh +1
In many sharing-economy applications, as well as in conventional economy applications, one wishes to regulate the behaviour of an ensemble of agents with guarantees on both the reg…