3 citations · 14 across the 17 of their papers we have counts for
19 papers
New Bounds on Quantum Sample Complexity of Measurement Classes
Mohsen Heidari, Wojciech Szpankowski
This paper studies quantum supervised learning for classical inference from quantum states. In this model, a learner has access to a set of labeled quantum samples as the training…
Efficient Gradient Estimation for Parameterized Quantum Systems with Lie Algebraic Symmetries
Mohsen Heidari, Masih Mozakka, Wojciech Szpankowski
Gradient estimation is a central challenge in training parameterized quantum circuits (PQCs) for hybrid quantum-classical optimization and learning problems. This difficulty arises…
Online Distribution Learning with Local Private Constraints
Jin Sima, Changlong Wu, Olgica Milenkovic +1
We study the problem of online conditional distribution estimation with \emph{unbounded} label sets under local differential privacy. Let be a distribution-valued fun…
Oracle-Efficient Hybrid Online Learning with Unknown Distribution
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. process and the labels are generated adversarially. Assuming ac…
Quantum Shadow Gradient Descent for Variational Quantum Algorithms
Mohsen Heidari, Mobasshir A Naved, Zahra Honjani +3
Gradient-based optimizers have been proposed for training variational quantum circuits in settings such as quantum neural networks (QNNs). The task of gradient estimation, however,…
Robust Online Classification: From Estimation to Denoising
Changlong Wu, Ananth Grama, Wojciech Szpankowski
We study online classification of features into labels with general hypothesis classes. In our setting, true labels are determined by some function within the hypothesis class but…
On the concentration of the maximum degree in the duplication-divergence models
Alan Frieze, Krzysztof Turowski, Wojciech Szpankowski
We present a rigorous and precise analysis of the maximum degree and the average degree in a dynamic duplication-divergence graph model introduced by Solé, Pastor-Satorras et al. i…
Agnostic PAC Learning of k-juntas Using L2-Polynomial Regression
Mohsen Heidari, Wojciech Szpankowski
Many conventional learning algorithms rely on loss functions other than the natural 0-1 loss for computational efficiency and theoretical tractability. Among them are approaches ba…
Online Learning in Dynamically Changing Environments
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. We introduce the concept of a dynamic c…
Towards a Unification of Logic and Information Theory
Luis A. Lastras, Barry Trager, Jonathan Lenchner +5
Today, the vast majority of the world's digital information is represented using the fundamental assumption, introduced by Claude Shannon in 1948, that ``...the semantic aspects of…
Expected Worst Case Regret via Stochastic Sequential Covering
Changlong Wu, Mohsen Heidari, Ananth Grama +1
We study the problem of sequential prediction and online minimax regret with stochastically generated features under a general loss function. We introduce a notion of expected wors…
Precise Regret Bounds for Log-loss via a Truncated Bayesian Algorithm
Changlong Wu, Mohsen Heidari, Ananth Grama +1
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. We f…
Toward Physically Realizable Quantum Neural Networks
Mohsen Heidari, Ananth Grama, Wojciech Szpankowski
There has been significant recent interest in quantum neural networks (QNNs), along with their applications in diverse domains. Current solutions for QNNs pose significant challeng…
A Theoretical Framework for Learning from Quantum Data
Mohsen Heidari, Arun Padakandla, Wojciech Szpankowski
Over decades traditional information theory of source and channel coding advances toward learning and effective extraction of information from data. We propose to go one step furth…
On Agnostic PAC Learning using -polynomial Regression and Fourier-based Algorithms
Mohsen Heidari, Wojciech Szpankowski
We develop a framework using Hilbert spaces as a proxy to analyze PAC learning problems with structural properties. We consider a joint Hilbert space incorporating the relation bet…
Learning k-qubit Quantum Operators via Pauli Decomposition
Mohsen Heidari, Wojciech Szpankowski
Motivated by the limited qubit capacity of current quantum systems, we study the quantum sample complexity of -qubit quantum operators, i.e., operations applicable on only o…
Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning
Gil I. Shamir, Wojciech Szpankowski
Theoretical results show that Bayesian methods can achieve lower bounds on regret for online logistic regression. In practice, however, such techniques may not be feasible especial…
On maximum-likelihood estimation in the all-or-nothing regime
Luca Corinzia, Paolo Penna, Wojciech Szpankowski +1
We study the problem of estimating a rank-1 additive deformation of a Gaussian tensor according to the \emph{maximum-likelihood estimator} (MLE). The analysis is carried out in the…
Statistical and computational thresholds for the planted -densest sub-hypergraph problem
Luca Corinzia, Paolo Penna, Wojciech Szpankowski +1
In this work, we consider the problem of recovery a planted -densest sub-hypergraph on -uniform hypergraphs. This fundamental problem appears in different contexts, e.g., com…