3 citations · 6 across the 19 of their papers we have counts for
28 papers · 1 filter
Functional Properties of the Focal-Entropy
Jaimin Shah, Martina Cardone, Alex Dytso
The focal-loss has become a widely used alternative to cross-entropy in class-imbalanced classification problems, particularly in computer vision. Despite its empirical success, a…
An Improved Lower Bound on Cardinality of Support of the Amplitude-Constrained AWGN Channel
Haiyang Wang, Luca Barletta, Alex Dytso
We study the amplitude-constrained additive white Gaussian noise channel. It is well known that the capacity-achieving input distribution for this channel is discrete and supported…
A Rate-Distortion Bound for ISAC
Mohammadreza Bakhshizadeh Mohajer, Alex Dytso, Daniela Tuninetti +1
This paper addresses the fundamental performance limits of Integrated Sensing and Communication (ISAC) systems by introducing a novel converse bound based on rate-distortion theory…
Lossy Source Coding with Focal Loss
Alex Dytso, Martina Cardone
Focal loss has recently gained significant popularity, particularly in tasks like object detection where it helps to address class imbalance by focusing more on hard-to-classify ex…
Estimation Error: Distribution and Pointwise Limits
Luca Barletta, Alex Dytso, Shlomo Shamai
In this paper, we examine the distribution and convergence properties of the estimation error , where is the Bayesian estimator of a random variabl…
An MMSE Lower Bound via Poincaré Inequality
Ian Zieder, Alex Dytso, Martina Cardone
This paper studies the minimum mean squared error (MMSE) of estimating from the noisy observation , under the assumption…