Related papers: Profile Likelihoods on ML-Steroids

In post-training for reasoning Large Language Models (LLMs), the current state of practice trains LLMs in two independent stages: Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR, shortened as ``RL''…

Systematic review (SR) is a popular research method in software engineering (SE). However, conducting an SR takes an average of 67 weeks. Thus, automating any step of the SR process could reduce the effort associated with SRs. Our objective…

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

Stochastic simulation techniques employed for the analysis of portfolios of insurance/reinsurance risk, often referred to as `Aggregate Risk Analysis', can benefit from exploiting state-of-the-art high-performance computing platforms. In…

Privacy protection has become an increasing concern in modern machine learning applications. Privacy-preserving machine learning (PPML) has attracted growing research attention, with approaches such as secure multiparty computation (MPC)…

Feature importance scores are ubiquitous tools for understanding the predictions of machine learning models. However, many popular attribution methods suffer from high instability due to random sampling. Leveraging novel ideas from…

Profile guided optimization is an effective technique for improving the optimization ability of compilers based on dynamic behavior, but collecting profile data is expensive, cumbersome, and requires regular updating to remain fresh. We…

In this paper we consider the problem of computing the likelihood of the profile of a discrete distribution, i.e., the probability of observing the multiset of element frequencies, and computing a profile maximum likelihood (PML)…

The entry of large language models (LLMs) into research and commercial spaces has led to a trend of ever-larger models, with initial promises of generalisability, followed by a widespread desire to downsize and create specialised models…

Symbolic regression is a nonlinear regression method which is commonly performed by an evolutionary computation method such as genetic programming. Quantification of uncertainty of regression models is important for the interpretation of…

Reliability is a fundamental challenge in operating large-scale machine learning (ML) infrastructures, particularly as the scale of ML models and training clusters continues to grow. Despite decades of research on infrastructure failures,…

Research profiles highlight scientists' research focus, enabling talent discovery and collaborations, but are often outdated. Automated, scalable methods are urgently needed to keep profiles current. We design and evaluate two Large…

Currently, many verification algorithms are available to improve the reliability of software systems. Selecting the appropriate verification algorithm typically demands domain expertise and non-trivial manpower. An automated algorithm…

The advent of data science has spurred interest in estimating properties of distributions over large alphabets. Fundamental symmetric properties such as support size, support coverage, entropy, and proximity to uniformity, received most…

Machine learning (ML) inference serving systems can schedule requests to improve GPU utilization and to meet service level objectives (SLOs) or deadlines. However, improving GPU utilization may compromise latency-sensitive scheduling, as…

While high-level languages come with significant readability and maintainability benefits, their performance remains difficult to predict. For example, programmers may unknowingly use language features inappropriately, which cause their…

Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of…

Machine learning force fields (MLFFs) are gradually evolving towards enabling molecular dynamics simulations of molecules and materials with ab initio accuracy but at a small fraction of the computational cost. However, several challenges…

The NLI4CT task assesses Natural Language Inference systems in predicting whether hypotheses entail or contradict evidence from Clinical Trial Reports. In this study, we evaluate various Large Language Models (LLMs) with multiple…

Machine learning (ML) enables the development of interatomic potentials that promise the accuracy of first principles methods while retaining the low cost and parallel efficiency of empirical potentials. While ML potentials traditionally…