Search Results for author:
Found 21 papers, 1 papers with code
On Theoretical Limits of Learning with Label Differential Privacy
Our results demonstrate that under label local DP (LDP), the risk has a significantly faster convergence rate than that under full LDP, i. e. protecting both features and labels, indicating the advantages of relaxing the DP definition to focus solely on labels.
Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets
In a real federated learning (FL) system, communication overhead for passing model parameters between the clients and the parameter server (PS) is often a bottleneck.
Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates
The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting in a superfluous factor of $d$ in the union bound.
Contextual Bandits for Unbounded Context Distributions
In this paper, we solve the nonparametric contextual bandit problem with unbounded contexts.
Byzantine-resilient Federated Learning Employing Normalized Gradients on Non-IID Datasets
In cases where the loss function is strongly convex, the zero optimality gap achieving rate can be improved to be linear.
Learning with User-Level Local Differential Privacy
Under the central model, user-level DP is strictly stronger than the item-level one.
Enhancing Learning with Label Differential Privacy by Vector Approximation
Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public.
CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models
The success of current Large-Language Models (LLMs) hinges on extensive training data that is collected and stored centrally, called Centralized Learning (CL).
Emulating Full Client Participation: A Long-Term Client Selection Strategy for Federated Learning
In this study, we propose a novel client selection strategy designed to emulate the performance achieved with full client participation.
A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
We provide a theoretical analysis of our approach, which gives the noise strength needed for privacy protection, as well as the bound of mean squared error.
Soft Label PU Learning
In this paper, we propose soft label PU learning, in which unlabeled data are assigned soft labels according to their probabilities of being positive.
Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection
Most models for weakly supervised video anomaly detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly.
A Huber Loss Minimization Approach to Byzantine Robust Federated Learning
Federated learning systems are susceptible to adversarial attacks.
Minimax Optimal Q Learning with Nearest Neighbors
A recent interesting work \cite{shah2018q} solves MDP with bounded continuous state space by a nearest neighbor $Q$ learning approach, which has a sample complexity of $\tilde{O}(\frac{1}{\epsilon^{d+3}(1-\gamma)^{d+7}})$ for $\epsilon$-accurate $Q$ function estimation with discount factor $\gamma$.
High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers
In this paper, we design a new method that is suitable for high dimensional problems, under arbitrary number of Byzantine attackers.
Robust Nonparametric Regression under Poisoning Attack
The final estimate is nearly minimax optimal for arbitrary $q$, up to a $\ln N$ factor.
Optimal Stochastic Nonconvex Optimization with Bandit Feedback
In this paper, we analyze the continuous armed bandit problems for nonconvex cost functions under certain smoothness and sublevel set assumptions.
Analysis of KNN Density Estimation
We show that kNN density estimation is minimax optimal under both $\ell_1$ and $\ell_\infty$ criteria, if the support set is known.
Minimax Optimal Estimation of KL Divergence for Continuous Distributions
Estimating Kullback-Leibler divergence from identical and independently distributed samples is an important problem in various domains.
Minimax Rate Optimal Adaptive Nearest Neighbor Classification and Regression
For both classification and regression problems, existing works have shown that, if the distribution of the feature vector has bounded support and the probability density function is bounded away from zero in its support, the convergence rate of the standard kNN method, in which k is the same for all test samples, is minimax optimal.
Analysis of KNN Information Estimators for Smooth Distributions
Existing work has analyzed the convergence rate of this estimator for random variables whose densities are bounded away from zero in its support.
