Prompt-saw: Leveraging relation-aware graphs for textual prompt compression
Large Language Models (LLMs) have shown exceptional abilities for multiple different
natural language processing tasks. While prompting is a crucial tool for LLM inference, we …
natural language processing tasks. While prompting is a crucial tool for LLM inference, we …
Optimal Locally Private Nonparametric Classification with Public Data
In this work, we investigate the problem of public data assisted non-interactive Local
Differentially Private (LDP) learning with a focus on non-parametric classification. Under the …
Differentially Private (LDP) learning with a focus on non-parametric classification. Under the …
Dialectical alignment: Resolving the tension of 3h and security threats of llms
With the rise of large language models (LLMs), ensuring they embody the principles of being
helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While …
helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While …
[HTML][HTML] An effective federated object detection framework with dynamic differential privacy
B Wang, D Feng, J Su, S Song - Mathematics, 2024 - mdpi.com
The proliferation of data across multiple domains necessitates the adoption of machine
learning models that respect user privacy and data security, particularly in sensitive …
learning models that respect user privacy and data security, particularly in sensitive …
Private Language Models via Truncated Laplacian Mechanism
Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent
privacy leakage, researchers have investigated word-level perturbations, relying on the …
privacy leakage, researchers have investigated word-level perturbations, relying on the …
Truthful High Dimensional Sparse Linear Regression
We study the problem of fitting the high dimensional sparse linear regression model with sub-
Gaussian covariates and responses, where the data are provided by strategic or self …
Gaussian covariates and responses, where the data are provided by strategic or self …
Distributed Differentially Private Data Analytics via Secure Sketching
We explore the use of distributed differentially private computations across multiple servers,
balancing the tradeoff between the error introduced by the differentially private mechanism …
balancing the tradeoff between the error introduced by the differentially private mechanism …
PAC learning halfspaces in non-interactive local differential privacy model with public unlabeled data
In this paper, we study the problem of PAC learning halfspaces in the non-interactive local
differential privacy model (NLDP). To breach the barrier of exponential sample complexity …
differential privacy model (NLDP). To breach the barrier of exponential sample complexity …
Gradient complexity and non-stationary views of differentially private empirical risk minimization
In this paper, we study the Differentially Private Empirical Risk Minimization (DP-ERM)
problem, considering both convex and non-convex loss functions. For cases where DP-ERM …
problem, considering both convex and non-convex loss functions. For cases where DP-ERM …
On the Optimal Regret of Locally Private Linear Contextual Bandit
J Li, D Simchi-Levi, Y Wang - arXiv preprint arXiv:2404.09413, 2024 - arxiv.org
Contextual bandit with linear reward functions is among one of the most extensively studied
models in bandit and online learning research. Recently, there has been increasing interest …
models in bandit and online learning research. Recently, there has been increasing interest …