Related papers: PraxiMLP: A Threshold-based Framework for Efficien…

In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks. Existing solutions either involve a trusted aggregator or require heavyweight cryptographic primitives, which degrades performance…

In this study, we propose a two-party computation protocol for approximate matrix multiplication of fixed-point numbers. The proposed protocol is provably secure under standard lattice-based cryptographic assumptions and enables matrix…

Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale…

Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding space. We relate DML to feasibility problem of finite chance constraints. We show that minimizer…

Leveraging Large Language Models (LLMs) to write policy code for controlling robots has gained significant attention. However, in long-horizon implicative tasks, this approach often results in API parameter, comments and sequencing errors,…

With the rapid increase in computing, storage and networking resources, data is not only collected and stored, but also analyzed. This creates a serious privacy problem which often inhibits the use of this data. In this chapter, we…

Quantum machine learning (QML) is a promising paradigm for tackling computational problems that challenge classical AI. Yet, the inherent probabilistic behavior of quantum mechanics, device noise in NISQ hardware, and hybrid…

We propose an efficient algorithm for approximate computation of the profile maximum likelihood (PML), a variant of maximum likelihood maximizing the probability of observing a sufficient statistic rather than the empirical sample. The PML…

Large language models (LLMs) have recently demonstrated remarkable progress in formal theorem proving. Yet their ability to serve as practical assistants for mathematicians, filling in missing steps within complex proofs, remains…

Devising dynamic pricing policy with always valid online statistical learning procedure is an important and as yet unresolved problem. Most existing dynamic pricing policy, which focus on the faithfulness of adopted customer choice models,…

Training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters requires tens of thousands of GPUs, and a highly scalable software stack. In this work, we present a novel four-dimensional hybrid…

Portability, performance, and productivity are three critical dimensions for evaluating a programming model or compiler infrastructure. Several modern programming models for computational science focus on performance and portability. On the…

Nowadays, gathering high-quality training data from multiple data sources with privacy preservation is a crucial challenge to training high-performance machine learning models. The potential solutions could break the barriers among isolated…

Prompt optimization has become crucial for enhancing the performance of large language models (LLMs) across a broad range of tasks. Although many research papers demonstrate its effectiveness, practical adoption is hindered because existing…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and languages. However, the fine-tuning of multilingual LLMs,…

Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises…

Log parsing is a critical step that transforms unstructured log data into structured formats, facilitating subsequent log-based analysis. Traditional syntax-based log parsers are efficient and effective, but they often experience decreased…

The deep metric learning (DML) objective is to learn a neural network that maps into an embedding space where similar data are near and dissimilar data are far. However, conventional proxy-based losses for DML have two problems: gradient…

Replicability in machine learning (ML) research is increasingly concerning due to the utilization of complex non-deterministic algorithms and the dependence on numerous hyper-parameter choices, such as model architecture and training…