Related papers: Opus: A Quantitative Framework for Workflow Evalua…

This paper is concerned with optimal power flow (OPF), which is the problem of optimizing the transmission of electricity in power systems. Our main contributions are as follows: (i) we propose a novel parabolic relaxation, which transforms…

As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either rely on heuristic static filters that ignore training…

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Off-policy estimation (OPE) methods enable unbiased offline evaluation of recommender systems, directly estimating the online reward some target policy would have obtained, from offline data and with statistical guarantees. The theoretical…

Sparse estimation methods are aimed at using or obtaining parsimonious representations of data or models. They were first dedicated to linear variable selection but numerous extensions have now emerged such as structured sparsity or kernel…

Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting data incurs unnecessary present costs, while under-collecting…

Benchmarks for the evaluation of model performance play an important role in machine learning. However, there is no established way to describe and create new benchmarks. What is more, the most common benchmarks use performance measures…

An established trend in software engineering insists on using components (sometimes also called services or packages) to encapsulate a set of related functionalities or data. By defining interfaces specifying what functionalities they…

Model performance evaluation is a critical and expensive task in machine learning and computer vision. Without clear guidelines, practitioners often estimate model accuracy using a one-time completely random selection of the data. However,…

Offline reinforcement learning (RL) aims to optimize a policy using collected data without online interactions. Model-based approaches are particularly appealing for addressing offline RL challenges because of their capability to mitigate…

In large distributed systems, failures are a daily event occurring frequently, especially with growing numbers of computation tasks and locations on which they are deployed. The advantage of representing an application with a workflow is…

Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results are often inconsistent and difficult to replicate. In this…

We propose a computational framework to quantify (measure) and to optimize the reliability of complex systems. The approach uses a graph representation of the system that is subject to random failures of its components (nodes and edges).…

Our ongoing development and deployment of an online robotics education platform highlighted a gap in providing an interactive, feedback-rich learning environment essential for mastering programming concepts in robotics, which they were not…

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Optimization of expensive computer models with the help of Gaussian process emulators in now commonplace. However, when several (competing) objectives are considered, choosing an appropriate sampling strategy remains an open question. We…

Emerging IoT-enabled cyber-physical applications demand low-latency, energy-efficient, and reliable execution across resource-constrained edge devices with heterogeneous multicore processors and diverse sensing and actuating capabilities,…

Proximal Policy Optimization (PPO)-based reinforcement learning from human feedback (RLHF) is a widely adopted paradigm for aligning large language models (LLMs) with human preferences. However, its training pipeline suffers from…

The convergence of IoT, Edge, Cloud, and HPC technologies creates a compute continuum that merges cloud scalability and flexibility with HPC's computational power and specialized optimizations. However, integrating cloud and HPC resources…

In the current paper, we present an optimization system solving multi objective production scheduling problems (MOOPPS). The identification of Pareto optimal alternatives or at least a close approximation of them is possible by a set of…