Related papers: MMO: Meta Multi-Objectivization for Software Confi…

We study the problem of optimizing a function under a \emph{budgeted number of evaluations}. We only assume that the function is \emph{locally} smooth around one of its global optima. The difficulty of optimization is measured in terms of…

Hyperparameter optimization (HPO) aims to identify an optimal hyperparameter configuration (HPC) such that the resulting model generalizes well to unseen data. As the expected generalization error cannot be optimized directly, it is…

Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must…

Learning and predicting the performance of given software configurations are of high importance to many software engineering activities. While configurable software systems will almost certainly face diverse running environments (e.g.,…

For many machine learning models, a choice of hyperparameters is a crucial step towards achieving high performance. Prevalent meta-learning approaches focus on obtaining good hyperparameters configurations with a limited computational…

Selecting the best data mixture is critical for successful Supervised Fine-Tuning (SFT) of Multimodal Large Language Models. However, determining the optimal mixture weights across multiple domain-specific datasets remains a significant…

Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch between pre-collected offline preference data and the…

We present a review that unifies decision-support methods for exploring the solutions produced by multi-objective optimization (MOO) algorithms. As MOO is applied to solve diverse problems, approaches for analyzing the trade-offs offered by…

Automatic performance tuning (auto-tuning) is widely used to optimize performance-critical applications across many scientific domains by finding the best program variant among many choices. Efficient optimization algorithms are crucial for…

Pareto front profiling in multi-objective optimization (MOO), i.e., finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives that require training a neural network. Typically, in MOO for neural…

We propose a framework for online meta-optimization of parameters that govern optimization, called Amortized Proximal Optimization (APO). We first interpret various existing neural network optimizers as approximate stochastic proximal point…

Tuning a database system to achieve optimal performance on a given workload is a long-standing problem in the database community. A number of recent works have leveraged ML-based approaches to guide the sampling of large parameter spaces…

The exponential growth in LLM scales, with parameters soaring from billions to trillions, has necessitated distributed pretraining across large clusters comprising thousands to tens of thousands of devices. While hybrid parallelization…

Parametric multi-objective optimization (PMO) addresses the challenge of solving an infinite family of multi-objective optimization problems, where optimal solutions must adapt to varying parameters. Traditional methods require re-execution…

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

In contrast to single-objective optimization (SOO), multi-objective optimization (MOO) requires an optimizer to find the Pareto frontier, a subset of feasible solutions that are not dominated by other feasible solutions. In this paper, we…

This paper proposes MOON (Multi-Objective Optimization-driven Object-goal Navigation), a novel framework designed for efficient navigation in large-scale, complex indoor environments. While existing methods often rely on local heuristics,…

Recent research explores optimization using large language models (LLMs) by either iteratively seeking next-step solutions from LLMs or directly prompting LLMs for an optimizer. However, these approaches exhibit inherent limitations,…

Dynamic multi-objective optimization (DMOO) has recently attracted increasing interest from both academic researchers and engineering practitioners, as numerous real-world applications that evolve over time can be naturally formulated as…

Expensive multi-objective optimization is a prevalent and crucial concern in many real-world scenarios, where sample-efficiency is vital due to the limited evaluations to recover the true Pareto front for decision making. Existing works…