相关论文: Bicoptor 2.0: Addressing Challenges in Probabilist…

Personalized Federated Learning (PFL) is widely employed in IoT applications to handle high-volume, non-iid client data while ensuring data privacy. However, heterogeneous edge devices owned by clients may impose varying degrees of resource…

Longitudinal data tracking under Local Differential Privacy (LDP) is a challenging task. Baseline solutions that repeatedly invoke a protocol designed for one-time computation lead to linear decay in the privacy or utility guarantee with…

In this paper, we study a fixed-confidence, fixed-tolerance formulation of a class of stochastic bi-level optimization problems, where the upper-level problem selects from a finite set of systems based on a performance metric, and the…

Private record linkage (PRL) is the problem of identifying pairs of records that are similar as per an input matching rule from databases held by two parties that do not trust one another. We identify three key desiderata that a PRL…

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…

The growing demand for efficient deep learning has positioned dataset distillation as a pivotal technique for compressing training dataset while preserving model performance. However, existing inner-loop optimization methods for dataset…

As large language models (LLMs) are increasingly adopted in safety-critical and regulated sectors, the retention of sensitive or prohibited knowledge introduces escalating risks, ranging from privacy leakage to regulatory non-compliance to…

Deep neural networks (DNNs) have successfully learned useful data representations in various tasks. However, assessing the reliability of these representations remains a challenge. Deep Ensemble is widely considered the state-of-the-art…

Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs), particularly to enhance their reasoning capabilities. However, RL fine-tuning remains highly resource-intensive, and existing work…

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving…

The Primal-Dual (PD) algorithm is widely used in convex optimization to determine saddle points. While the stability of the PD algorithm can be easily guaranteed, strict contraction is nontrivial to establish in most cases. This work…

Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \textit{Probabilistic embeddings for actor-critic RL}…

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on large offline datasets, incurring high collection costs and offering suboptimal…

Finding efficient, easily implementable differentially private (DP) algorithms that offer strong excess risk bounds is an important problem in modern machine learning. To date, most work has focused on private empirical risk minimization…

The increasing scale of general-purpose Pre-trained Language Models (PLMs) necessitates the study of more efficient adaptation across different downstream tasks. In this paper, we establish a Black-box Discrete Prompt Learning (BDPL) to…

Secure multi-party computation-based machine learning, referred to as MPL, has become an important technology to utilize data from multiple parties with privacy preservation. While MPL provides rigorous security guarantees for the…

In this paper, we address the problem of privacy-preserving federated neural network training with $N$ users. We present Hercules, an efficient and high-precision training framework that can tolerate collusion of up to $N-1$ users. Hercules…

In recommender systems, users always choose the favorite items to rate, which leads to data missing not at random and poses a great challenge for unbiased evaluation and learning of prediction models. Currently, the doubly robust (DR)…

Compression is a crucial solution for data reduction in modern scientific applications due to the exponential growth of data from simulations, experiments, and observations. Compression with progressive retrieval capability allows users to…