Related papers: MOPO-LSI: A User Guide
Programmatic hyperparameter optimization (HPO) methods, such as Bayesian optimization and evolutionary algorithms, are highly sample-efficient in identifying optimal hyperparameter configurations for machine learning (ML) models. However,…
Existing open-source multimodal large language models (MLLMs) generally follow a training process involving pre-training and supervised fine-tuning. However, these models suffer from distribution shifts, which limit their multimodal…
The README file serves as a critical source of information for gaining an overview and helping developers onboard to an Open Source Software (OSS) project. Yet, documentation issues persist; in particular, ``outdated'' documentation is…
This user manual has been written to describe the open source code WM to be distributed associated with a research article submitted to the information technology journal 45001-ITJ-ANSI, entitled: "Maintenance and Reengineering of software:…
MuSim is a new user-friendly program designed to interface to many different particle simulation codes, regardless of their data formats or geometry descriptions. It presents the user with a compelling graphical user interface that includes…
Recommendation for new users, also called user cold start, has been a well-recognized challenge for online recommender systems. Most existing methods view the crux as the lack of initial data. However, in this paper, we argue that there are…
In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization. Existing gradient-based…
Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can enhance training,…
Machine learning (ML) methods offer a wide range of configurable hyperparameters that have a significant influence on their performance. While accuracy is a commonly used performance objective, in many settings, it is not sufficient.…
The data model of an application, the nature and format of data stored across executions, is typically a very rigid part of its early specification, even when prototyping, and changing it after code that relies on it was written can prove…
Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become one of the most widely used algorithms for achieving this…
Model inversion attacks pose a significant privacy risk by attempting to reconstruct private training data from trained models. Most of the existing methods either depend on gradient estimation or require white-box access to model…
SWI-Prolog is neither a commercial Prolog system nor a purely academic enterprise, but increasingly a community project. The core system has been shaped to its current form while being used as a tool for building research prototypes,…
Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization…
In today's dynamic technological landscape, sustainability has emerged as a pivotal concern, especially with respect to architecting Machine Learning enabled Systems (MLS). Many ML models fail in transitioning to production, primarily…
This article provides a brief overview of the UML SP (UML Scientific Profile). It is an Object-Oriented Simulation Language and may find usage in OOS and ABS. UML SP allows for the application of Unified Process methodology for the…
In this paper, we address the problem of cost-sensitive multi-fidelity Bayesian Optimization (BO) for efficient hyperparameter optimization (HPO). Specifically, we assume a scenario where users want to early-stop the BO when the performance…
Machine learning approaches, enabled by the emergence of comprehensive databases of materials properties, are becoming a fruitful direction for materials analysis. As a result, a plethora of models have been constructed and trained on…
Multiobjective control design is known to be a difficult problem both in theory and practice. Our approach is to search for locally optimal solutions of a nonsmooth optimization problem that is built to incorporate minimization objectives…
Decomposition has become an increasingly popular technique for evolutionary multi-objective optimization (EMO). A decomposition-based EMO algorithm is usually designed to approximate a whole Pareto-optimal front (PF). However, in practice,…