Search Results for author:
Found 17 papers, 1 papers with code
Adversarial Quantum Machine Learning: An Information-Theoretic Generalization Analysis
Specifically, a quantum adversary maximizes the classifier's loss by transforming an input state $\rho(x)$ into a state $\lambda$ that is $\epsilon$-close to the original state $\rho(x)$ in $p$-Schatten distance.
Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis
We explore a stochastic contextual linear bandit problem where the agent observes a noisy, corrupted version of the true context through a noise channel with an unknown noise parameter.
Statistical Complexity of Quantum Learning
Recent years have seen significant activity on the problem of using data for the purpose of learning properties of quantum systems or of processing classical or quantum data via quantum computing.
Bayesian and Multi-Armed Contextual Meta-Optimization for Efficient Wireless Radio Resource Management
Optimal resource allocation in modern communication networks calls for the optimization of objective functions that are only accessible via costly separate evaluations for each candidate solution.
Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems
This review monograph provides an introduction to meta-learning by covering principles, algorithms, theory, and engineering applications.
Error Mitigation-Aided Optimization of Parameterized Quantum Circuits: Convergence Analysis
It is shown that quantum gate noise induces a non-zero error-floor on the convergence error of SGD (evaluated with respect to a reference noiseless PQC), which depends on the number of noisy gates, the strength of the noise, as well as the eigenspectrum of the observable being measured and minimized.
Transfer Learning for Quantum Classifiers: An Information-Theoretic Generalization Analysis
An upper bound on the optimality gap is derived in terms of the proposed task (dis)similarity measure, two R$\'e$nyi mutual information terms between classical input and quantum embedding under source and target tasks, as well as a measure of complexity of the combined space of quantum embeddings and classifiers under the source task.
An Information-Theoretic Analysis of The Cost of Decentralization for Learning and Inference Under Privacy Constraints
In vertical federated learning (FL), the features of a data sample are distributed across multiple agents.
Transfer Bayesian Meta-learning via Weighted Free Energy Minimization
Meta-learning optimizes the hyperparameters of a training procedure, such as its initialization, kernel, or learning rate, based on data sampled from a number of auxiliary tasks.
A unified PAC-Bayesian framework for machine unlearning via information risk minimization
Machine unlearning refers to mechanisms that can remove the influence of a subset of training data upon request from a trained model without incurring the cost of re-training from scratch.
Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning
Under a Bayesian formulation, assuming a well-specified model, the two contributions can be exactly expressed (for the log-loss) or bounded (for more general losses) in terms of information-theoretic quantities (Xu and Raginsky, 2020).
An Information-Theoretic Analysis of the Impact of Task Similarity on Meta-Learning
The goal of the meta-learner is to ensure that the hyperparameters obtain a small loss when applied for training of a new task sampled from the task environment.
Free Energy Minimization: A Unified Framework for Modelling, Inference, Learning,and Optimization
The goal of these lecture notes is to review the problem of free energy minimization as a unified framework underlying the definition of maximum entropy modelling, generalized Bayesian inference, learning with latent variables, statistical learning analysis of generalization, and local optimization.
Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization
In this paper, we introduce the problem of transfer meta-learning, in which tasks are drawn from a target task environment during meta-testing that may differ from the source task environment observed during meta-training.
Conditional Mutual Information-Based Generalization Bound for Meta Learning
Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks.
Information-Theoretic Bounds on Transfer Generalization Gap Based on Jensen-Shannon Divergence
In transfer learning, training and testing data sets are drawn from different data distributions.
Information-Theoretic Generalization Bounds for Meta-Learning and Applications
Extending the existing work for conventional learning, an upper bound on the meta-generalization gap is derived for the former class that depends on the mutual information (MI) between the output of the meta-learning algorithm and its input meta-training data.
