no code implementations • 7 Apr 2024 • Mohsen Heidari, Masih Mozakka, Wojciech Szpankowski
Hybrid quantum-classical optimization and learning strategies are among the most promising approaches to harnessing quantum information or gaining a quantum advantage over classical methods.
no code implementations • 10 Oct 2023 • Mohsen Heidari, Mobasshir A Naved, WenBo Xie, Arjun Jacob Grama, Wojciech Szpankowski
We propose a new technique for generating quantum shadow samples (QSS), which generates quantum shadows as opposed to classical shadows used in existing works.
no code implementations • 8 Mar 2023 • Mohsen Heidari, Wojciech Szpankowski
We derive an elegant upper bound on the 0-1 loss in terms of the MMSE error and show that the sign of the MMSE is a PAC learner for any concept class containing it.
no code implementations • 9 Sep 2022 • Changlong Wu, Mohsen Heidari, Ananth Grama, Wojciech Szpankowski
We show that for a hypothesis class of VC-dimension $\mathsf{VC}$ and $i. i. d.$ generated features of length $T$, the cardinality of the stochastic global sequential covering can be upper bounded with high probability (whp) by $e^{O(\mathsf{VC} \cdot \log^2 T)}$.
no code implementations • 7 May 2022 • Changlong Wu, Mohsen Heidari, Ananth Grama, Wojciech Szpankowski
We study the sequential general online regression, known also as the sequential probability assignments, under logarithmic loss when compared against a broad class of experts.
no code implementations • 22 Mar 2022 • Mohsen Heidari, Ananth Grama, Wojciech Szpankowski
Current solutions for QNNs pose significant challenges concerning their scalability, ensuring that the postulates of quantum mechanics are satisfied and that the networks are physically realizable.
no code implementations • 11 Feb 2021 • Mohsen Heidari, Wojciech Szpankowski
We develop a framework using Hilbert spaces as a proxy to analyze PAC learning problems with structural properties.
no code implementations • 10 Feb 2021 • Mohsen Heidari, Wojciech Szpankowski
Our approach is based on the Pauli decomposition of quantum operators and a technique that we name Quantum Shadow Sampling (QSS) to reduce the sample complexity exponentially.
Quantum Physics Data Structures and Algorithms