Christos Thrampoulidis

Christos Thrampoulidis


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 May 2018 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
CTChristos Thrampoulidis
Christos Thrampoulidis
EAEhsan Abbasi
Ehsan Abbasi
BHBabak Hassibi
Babak Hassibi
A popular approach for estimating an unknown signal x0 ∈ ℝn from noisy, linear measurements y = Ax0 + z ∈ ℝ is via solving a so called regularized M-estimator: x:= arg minx L(y – Ax) + λf(x). Here, L is a convex loss function, f is a convex (typically, non-smooth) regularizer, and, λ > 0 is a regularizer parameter. We analyze the squared error performance ‖x – x0‖22 of such estimators in the high-dimensional proportional regime where m,n → ∞ and m/n → δ. The design matrix is assumed to have entries iid Gaussian; only minimal and rather mild regularity conditions are imposed on the loss function, the regularizer, and on the noise and signal distributions. We show that the squared error converges in probability to a nontrivial limit that is given as the solution to a minimax convex-concave optimization problem on four scalar optimization variables. We identify a new summary parameter, termed the expected Moreau envelope to play a central role in the error characterization. The precise nature of the results permits an accurate performance comparison between different instances of regularized M-estimators and allows to optimally tune the involved parameters (such as the regularizer parameter, the number of measurements, etc.). The key ingredient of our proof is the convex Gaussian min-max theorem (CGMT) which is a tight and strengthened version of a classical Gaussian comparison inequality that was proved by Gordon in 1988.

30 April 2018 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
CTChristos Thrampoulidis
Christos Thrampoulidis
WXWeiyu Xu
Weiyu Xu
BHBabak Hassibi
Babak Hassibi
The maximum-likelihood (ML) decoder for symbol detection in large multiple-input multiple-output wireless communication systems is typically computationally prohibitive. In this paper, we study a popular and practical alternative, namely the box-relaxation optimization (BRO) decoder, which is a natural convex relaxation of the ML. For iid real Gaussian channels with additive Gaussian noise, we obtain exact asymptotic expressions for the symbol error rate (SER) of the BRO. The formulas are particularly simple, they yield useful insights, and they allow accurate comparisons to the matched-filter bound (MFB) and to linear decoders, such as zero-forcing and linear minimum mean square error. For BPSK signals the SER performance of the BRO is within 3dB of the MFB for square systems, and it approaches the MFB as the number of receive antennas grows large compared to the number of transmit antennas. Our analysis further shows that error events for any fixed number of symbols are asymptotically independent. The fundamental tool behind the analysis is the convex Gaussian min-max theorem.

24 April 2018 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Closed access
CTChristos Thrampoulidis
Christos Thrampoulidis
GSGal Shulkind
Gal Shulkind
FXFeihu Xu
Feihu Xu
WFWilliam T. Freeman
William T. Freeman
JSJeffrey H Shapiro
Jeffrey H Shapiro
GWGregory W. Wornell
Gregory W. Wornell
Active non-line-of-sight imaging systems are of growing interest for diverse applications. The most commonly proposed approaches to date rely on exploiting time-resolved measurements, i.e., measuring the time it takes for short-duration light pulses to transit the scene. This typically requires expensive, specialized, ultrafast lasers and detectors that must be carefully calibrated. We develop an alternative approach that exploits the valuable role that natural occluders in a scene play in enabling accurate and practical image formation in such settings without such hardware complexity. In particular, we demonstrate that the presence of occluders in the hidden scene can obviate the need for collecting time-resolved measurements, and develop an accompanying analysis for such systems and their generalizations. Ultimately, the results suggest the potential to develop increasingly sophisticated future systems that are able to identify and exploit diverse structural features of the environment to reconstruct scenes hidden from view.

17 January 2020 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
CTChristos Thrampoulidis
Christos Thrampoulidis
ARAnkit Singh Rawat
Ankit Singh Rawat
In the problem of structured signal recovery from high-dimensional linear observations, it is commonly assumed that full-precision measurements are available. Under this assumption, the recovery performance of the popular Generalized Lasso (G-Lasso) is by now well-established. In this paper, we extend these types of results to the practically relevant settings with quantized measurements. We study two extremes of the quantization schemes, namely, uniform and one-bit quantization; the former imposes no limit on the number of quantization bits, while the second only allows for one bit. In the presence of a uniform dithering signal and when measurement vectors are sub-gaussian, we show that the same algorithm (i.e., the G-Lasso) has favorable recovery guarantees for both uniform and one-bit quantization schemes. Our theoretical results, shed light on the appropriate choice of the range of values of the dithering signal and accurately capture the error dependence on the problem parameters. For example, our error analysis shows that the G-Lasso with one-bit uniformly dithered measurements leads to only a logarithmic rate loss compared to the full-precision measurements.

16 June 2021 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
AMAhmadreza Moradipari
Ahmadreza Moradipari
SASanae Amani
Sanae Amani
MAMahnoosh Alizadeh
Mahnoosh Alizadeh
CTChristos Thrampoulidis
Christos Thrampoulidis
The design and performance analysis of bandit algorithms in the presence of stage-wise safety or reliability constraints has recently garnered significant interest. In this work, we consider the linear stochastic bandit problem under additional unknown linear safety constraints that need to be satisfied at each round. For this problem, we present and analyze a new safe algorithm based on linear Thompson Sampling (TS). Our analysis shows that, with high probability, the algorithm chooses actions that are safe at each round and achieve cumulative regret of order O (d 3/2 log 1/2 d ·T 1/2 log 3/2 T). Remarkably, this matches the regret bound provided by [1], [2] for the standard linear TS algorithm in the absence of safety constraints. Also, our analysis highlights how the inherently randomized nature of the TS selection rule suffices to properly expand the set of safe actions that the algorithm has access to at each round. In particular, we compare this behavior to alternative safe algorithms, which typically require distinct rounds of randomization that are dedicated to learning the unknown constraints.

1 March 2017
Verified
Conference Paper
Closed access
IAIsmail Ben Atitallah
Ismail Ben Atitallah
CTChristos Thrampoulidis
Christos Thrampoulidis
AKAbla Kammoun
Abla Kammoun
TATareq Y. Al-Naffouri
Tareq Y. Al-Naffouri
BHBabak Hassibi
Babak Hassibi
MAMohamed-Slim Alouini
Mohamed-Slim Alouini
This paper investigates the problem of recovering an n-dimensional BPSK signal x 0 ∈ {-1, 1} n from m-dimensional measurement vector y = Ax+z, where A and z are assumed to be Gaussian with iid entries. We consider two variants of decoders based on the regularized least squares followed by hard-thresholding: the case where the convex relaxation is from {-1, 1} n to ℝ n and the box constrained case where the relaxation is to [-1, 1] n . For both cases, we derive an exact expression of the bit error probability when n and m grow simultaneously large at a fixed ratio. For the box constrained case, we show that there exists a critical value of the SNR, above which the optimal regularizer is zero. On the other side, the regularization can further improve the performance of the box relaxation at low to moderate SNR regimes. We also prove that the optimal regularizer in the bit error rate sense for the unboxed case is nothing but the MMSE detector.