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 • 1 Feb 2024 • Jin Sima, Changlong Wu, Olgica Milenkovic, Wojciech Szpankowski
We study the problem of online conditional distribution estimation with \emph{unbounded} label sets under local differential privacy.
no code implementations • 27 Jan 2024 • Changlong Wu, Jin Sima, Wojciech Szpankowski
We study the problem of oracle-efficient hybrid online learning when the features are generated by an unknown i. i. d.
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 • 31 Jan 2023 • Changlong Wu, Ananth Grama, Wojciech Szpankowski
We study the problem of online learning and online regret minimization when samples are drawn from a general unknown non-stationary process.
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
no code implementations • 28 Jan 2021 • Gil I. Shamir, Wojciech Szpankowski
Various approximations that, for huge sparse feature sets, diminish the theoretical advantages, must be used.
no code implementations • 25 Jan 2021 • Luca Corinzia, Paolo Penna, Wojciech Szpankowski, Joachim M. Buhmann
The result follows from two main technical points: (i) the connection established between the MLE and the MMSE, using the first and second-moment methods in the constrained signal space, (ii) a recovery regime for the MMSE stricter than the simple error vanishing characterization given in the standard AoN, that is here proved as a general result.
no code implementations • 23 Nov 2020 • Luca Corinzia, Paolo Penna, Wojciech Szpankowski, Joachim M. Buhmann
In this work, we consider the problem of recovery a planted $k$-densest sub-hypergraph on $d$-uniform hypergraphs.
1 code implementation • 2 May 2019 • Krzysztof Turowski, Jithin K. Sreedharan, Wojciech Szpankowski
In temporal ordered clustering, given a single snapshot of a dynamic network in which nodes arrive at distinct time instants, we aim at partitioning its nodes into $K$ ordered clusters $\mathcal{C}_1 \prec \cdots \prec \mathcal{C}_K$ such that for $i<j$, nodes in cluster $\mathcal{C}_i$ arrived before nodes in cluster $\mathcal{C}_j$, with $K$ being a data-driven parameter and not known upfront.
no code implementations • 6 Apr 2019 • Abram Magner, Wojciech Szpankowski
Numerous networks in the real world change over time, in the sense that nodes and edges enter and leave the networks.