no code implementations • 1 Jan 2024 • Alireza Maleki, Hamed Shah-Mansouri, Babak H. Khalaj
Although DNN models deployed at the edge are promising to provide AI as a service with low latency, their cooperation is yet to be explored.
no code implementations • 29 Sep 2023 • Amir Hossein Saberi, Amir Najafi, Alireza Heidari, Mohammad Hosein Movasaghinia, Abolfazl Motahari, Babak H. Khalaj
From a theoretical standpoint, we apply our framework on the classification problem of a mixture of two Gaussians in $\mathbb{R}^d$, where in addition to the $m$ independent and labeled samples from the true distribution, a set of $n$ (usually with $n\gg m$) out of domain and unlabeled samples are given as well.
no code implementations • 9 Sep 2022 • Amir Hossein Saberi, Amir Najafi, Seyed Abolfazl Motahari, Babak H. Khalaj
Also, we theoretically show that in order to achieve this bound, it is sufficient to have $n\ge\left(K^2/\varepsilon^2\right)e^{\Omega\left(K/\mathrm{SNR}^2\right)}$ samples, where $\mathrm{SNR}$ stands for the signal-to-noise ratio.
no code implementations • 18 Oct 2018 • Amir Najafi, Saeed Ilchi, Amir H. Saberi, Seyed Abolfazl Motahari, Babak H. Khalaj, Hamid R. Rabiee
We study the sample complexity of learning a high-dimensional simplex from a set of points uniformly sampled from its interior.