no code implementations • 3 Dec 2023 • Gokberk Yaylali, Dionysios S. Kalogerias
On the other hand, ergodic-optimal resource allocation policies are often susceptible to the statistical dispersion of heavy-tailed fading channels, leading to relatively frequent drastic performance drops.
no code implementations • 1 May 2023 • Gokberk Yaylali, Dionysios S. Kalogerias
Stochastic allocation of resources in the context of wireless systems ultimately demands reactive decision making for meaningfully optimizing network-wide random utilities, while respecting certain resource constraints.
2 code implementations • 22 Apr 2023 • 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 shaping channels using a multitude of tunable passive reflective elements.
no code implementations • 22 Nov 2022 • 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 characterized.
1 code implementation • 30 Oct 2022 • 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 a challenging problem with several practical limitations.
no code implementations • 26 Apr 2022 • Konstantinos E. Nikolakakis, Farzin Haddadpour, Amin Karbasi, Dionysios S. Kalogerias
For nonconvex smooth losses, we prove that full-batch GD efficiently generalizes close to any stationary point at termination, and recovers the generalization error guarantees of stochastic algorithms with fewer assumptions.
no code implementations • 14 Feb 2022 • Konstantinos E. Nikolakakis, Farzin Haddadpour, Dionysios S. Kalogerias, Amin Karbasi
These bounds coincide with those for SGD, and rather surprisingly are independent of $d$, $K$ and the batch size $m$, under appropriate choices of a slightly decreased learning rate.
1 code implementation • 23 Aug 2021 • 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 networking setups involving multiple users with heterogeneous objectives and imprecise or even unknown models and/or channel statistics.
no code implementations • 29 Apr 2021 • 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 latter measured by the associated average predictive squared error variance ($\sev$), for every admissible estimator of choice.
no code implementations • 14 Dec 2020 • Dionysios S. Kalogerias
Conditional Value-at-Risk ($\mathrm{CV@R}$) is one of the most popular measures of risk, which has been recently considered as a performance criterion in supervised statistical learning, as it is related to desirable operational features in modern applications, such as safety, fairness, distributional robustness, and prediction error stability.
no code implementations • 12 Jun 2020 • Harshat Kumar, Dionysios S. Kalogerias, George J. Pappas, Alejandro Ribeiro
Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Markov decision processes.
no code implementations • 11 Jun 2020 • Kontantinos E. Nikolakakis, Dionysios S. Kalogerias, Or Sheffet, Anand D. Sarwate
First, we propose a (non-private) successive elimination algorithm for strictly optimal best-arm identification, we show that our algorithm is $\delta$-PAC and we characterize its sample complexity.
no code implementations • 19 Dec 2019 • Dionysios S. Kalogerias, Warren B. Powell
We then present a complete analysis of the $\textit{Free-MESSAGE}^{p}$ algorithm, which establishes convergence in a user-tunable neighborhood of the optimal solutions of the original problem for convex costs, as well as explicit convergence rates for convex, weakly convex, and strongly convex costs, and in a unified way.
no code implementations • 6 Dec 2019 • Dionysios S. Kalogerias, Luiz. F. O. Chamon, George J. Pappas, Alejandro Ribeiro
Despite the simplicity and intuitive interpretation of Minimum Mean Squared Error (MMSE) estimators, their effectiveness in certain scenarios is questionable.
no code implementations • 10 Nov 2019 • Dionysios S. Kalogerias, Mark Eisen, George J. Pappas, Alejandro Ribeiro
Upon further assuming the use of near-universal policy parameterizations, we also develop explicit bounds on the gap between optimal values of initial, infinite dimensional resource allocation problems, and dual values of their parameterized smoothed surrogates.
no code implementations • 20 Sep 2019 • Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate
Specifically, we show that the finite sample complexity of the Chow-Liu algorithm for ensuring exact structure recovery from noisy data is inversely proportional to the information threshold squared (provided it is positive), and scales almost logarithmically relative to the number of nodes over a given probability of failure.
no code implementations • 29 Jul 2019 • Anastasios Dimas, Dionysios S. Kalogerias, Athina P. Petropulu
To meet the quality-of-service guarantees of the network, a key prerequisite for beamforming is relay selection.
no code implementations • 11 Dec 2018 • Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate
In the absence of noise, predictive learning on Ising models was recently studied by Bresler and Karzand (2020); this paper quantifies how noise in the hidden model impacts the tasks of structure recovery and marginal distribution estimation by proving upper and lower bounds on the sample complexity.
no code implementations • 2 Apr 2018 • Dionysios S. Kalogerias, Warren B. Powell
2) Assuming a strongly convex cost, we show that, for fixed semideviation order $p>1$ and for $\epsilon\in\left[0, 1\right)$, the MESSAGEp algorithm achieves a squared-${\cal L}_{2}$ solution suboptimality rate of the order of ${\cal O}(n^{-\left(1-\epsilon\right)/2})$ iterations, where, for $\epsilon>0$, pathwise convergence is simultaneously guaranteed.
no code implementations • 10 Apr 2016 • Dionysios S. Kalogerias, Athina P. Petropulu
We revisit the development of grid based recursive approximate filtering of general Markov processes in discrete time, partially observed in conditionally Gaussian noise.
no code implementations • 16 Feb 2016 • Dionysios S. Kalogerias, Athina P. Petropulu
In this work, we study stability of distributed filtering of Markov chains with finite state space, partially observed in conditionally Gaussian noise.