81 citations · 175 across the 31 of their papers we have counts for
33 papers
Stochastic Resource Allocation via Dual Tail Waterfilling
Gokberk Yaylali, Dionysios S. Kalogerias
Optimal resource allocation in wireless systems still stands as a rather challenging task due to the inherent statistical characteristics of channel fading. On the one hand, minima…
Model-Free Learning of Two-Stage Beamformers for Passive IRS-Aided Network Design
Hassaan Hashmi, Spyridon Pougkakiotis, Dionysios S. Kalogerias
Electronically tunable metasurfaces, or Intelligent Reflective Surfaces (IRSs), are a popular technology for achieving high spectral efficiency in modern wireless systems by shapin…
An active-set method for sparse approximations. Part II: General piecewise-linear terms
Spyridon Pougkakiotis, Jacek Gondzio, Dionysios S. Kalogerias
In this paper we present an efficient active-set method for the solution of convex quadratic programming problems with general piecewise-linear terms in the objective, with applica…
Risk-Aware Stability of Discrete-Time Systems
Margaret P. Chapman, Dionysios S. Kalogerias
We develop a generalized stability framework for stochastic discrete-time systems, where the generality pertains to the ways in which the distribution of the state energy can be ch…
Model-Free Learning of Optimal Beamformers for Passive IRS-Assisted Sumrate Maximization
Hassaan Hashmi, Spyridon Pougkakiotis, Dionysios S. Kalogerias
Although Intelligent Reflective Surfaces (IRSs) are a cost-effective technology promising high spectral efficiency in future wireless networks, obtaining optimal IRS beamformers is…
Strong Duality in Risk-Constrained Nonconvex Functional Programming
Dionysis Kalogerias, Spyridon Pougkakiotis
We show that a wide class of risk-constrained nonconvex functional optimization problems exhibit strong duality, regardless of nonconvexity. We develop two novel results under dist…
A Zeroth-order Proximal Stochastic Gradient Method for Weakly Convex Stochastic Optimization
Spyridon Pougkakiotis, Dionysios S. Kalogerias
In this paper we analyze a zeroth-order proximal stochastic gradient method suitable for the minimization of weakly convex stochastic optimization problems. We consider nonsmooth a…
State-Output Risk-Constrained Quadratic Control of Partially Observed Linear Systems
Nikolas Koumpis, Anastasios Tsiamis, Dionysios Kalogerias
We propose a methodology for performing risk-averse quadratic regulation of partially observed Linear Time-Invariant (LTI) systems disturbed by process and output noise. To compens…
Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD
Konstantinos E. Nikolakakis, Farzin Haddadpour, Amin Karbasi +1
We provide sharp path-dependent generalization and excess risk guarantees for the full-batch Gradient Descent (GD) algorithm on smooth losses (possibly non-Lipschitz, possibly nonc…
Black-Box Generalization: Stability of Zeroth-Order Learning
Konstantinos E. Nikolakakis, Farzin Haddadpour, Dionysios S. Kalogerias +1
We provide the first generalization error analysis for black-box learning through derivative-free optimization. Under the assumption of a Lipschitz and smooth unknown loss, we cons…
An active-set method for sparse approximations. Part I: Separable terms
Spyridon Pougkakiotis, Jacek Gondzio, Dionysios S. Kalogerias
In this paper we present an active-set method for the solution of -regularized convex quadratic optimization problems. It is derived by combining a proximal method of multi…
Linear Quadratic Control with Risk Constraints
Anastasios Tsiamis, Dionysios S. Kalogerias, Alejandro Ribeiro +1
We propose a new risk-constrained formulation of the classical Linear Quadratic (LQ) stochastic control problem for general partially-observed systems. Our framework is motivated b…
Model-Free Learning of Optimal Deterministic Resource Allocations in Wireless Systems via Action-Space Exploration
Hassaan Hashmi, Dionysios S. Kalogerias
Wireless systems resource allocation refers to perpetual and challenging nonconvex constrained optimization tasks, which are especially timely in modern communications and networki…
Uncertainty Principles in Risk-Aware Statistical Estimation
Nikolas P. Koumpis, Dionysios S. Kalogerias
We present a new uncertainty principle for risk-aware statistical estimation, effectively quantifying the inherent trade-off between mean squared error ($\mse$) and risk, the latte…
Noisy Linear Convergence of Stochastic Gradient Descent for CV@R Statistical Learning under Polyak-Łojasiewicz Conditions
Dionysios S. Kalogerias
Conditional Value-at-Risk () is one of the most popular measures of risk, which has been recently considered as a performance criterion in supervised statistical lea…
Zeroth-order Deterministic Policy Gradient
Harshat Kumar, Dionysios S. Kalogerias, George J. Pappas +1
Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling…
Risk-Constrained Linear-Quadratic Regulators
Anastasios Tsiamis, Dionysios S. Kalogerias, Luiz F. O. Chamon +2
We propose a new risk-constrained reformulation of the standard Linear Quadratic Regulator (LQR) problem. Our framework is motivated by the fact that the classical (risk-neutral) L…
Risk-Aware MMSE Estimation
Dionysios S. Kalogerias, Luiz F. O. Chamon, George J. Pappas +1
Despite the simplicity and intuitive interpretation of Minimum Mean Squared Error (MMSE) estimators, their effectiveness in certain scenarios is questionable. Indeed, minimizing sq…
Zeroth-order Stochastic Compositional Algorithms for Risk-Aware Learning
Dionysios S. Kalogerias, Warren B. Powell
We present , the first zeroth-order algorithm for (weakly-)convex mean-semideviation-based risk-aware learning, which is also the first three-level zerot…
Model-Free Learning of Optimal Ergodic Policies in Wireless Systems
Dionysios S. Kalogerias, Mark Eisen, George J. Pappas +1
Learning optimal resource allocation policies in wireless systems can be effectively achieved by formulating finite dimensional constrained programs which depend on system configur…
Optimal Rates for Learning Hidden Tree Structures
Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate
We provide high probability finite sample complexity guarantees for hidden non-parametric structure learning of tree-shaped graphical models, whose hidden and observable nodes are…
Joint Beamforming and Dynamic Relay Positioning for mmWave Urban Communications
Anastasios Dimas, Dionysios S. Kalogerias, Athina P. Petropulu
The use of millimeter wave (mmWave) spectrum for commercial wireless communications is expected to offer data rates in the order of Gigabits-per-second, thus able to support future…
Predictive Learning on Hidden Tree-Structured Ising Models
Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate
We provide high-probability sample complexity guarantees for exact structure recovery and accurate predictive learning using noise-corrupted samples from an acyclic (tree-shaped) g…
Recursive Optimization of Convex Risk Measures: Mean-Semideviation Models
Dionysios S. Kalogerias, Warren B. Powell
We develop recursive, data-driven, stochastic subgradient methods for optimizing a new, versatile, and application-driven class of convex risk measures, termed here as mean-semidev…