相关论文: HPO: We won't get fooled again

Deep learning models form one of the most powerful machine learning models for the extraction of important features. Most of the designs of deep neural models, i.e., the initialization of parameters, are still manually tuned. Hence,…

Hyper-parameters optimization (HPO) is vital for machine learning models. Besides model accuracy, other tuning intentions such as model training time and energy consumption are also worthy of attention from data analytic service providers.…

In High Energy Physics (HEP), analysis metadata comes in many forms -- from theoretical cross-sections, to calibration corrections, to details about file processing. Correctly applying metadata is a crucial and often time-consuming step in…

This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions. In particular, this work studies how fairness propagates through a compound decision-making…

The hyper-parameter optimization (HPO) process is imperative for finding the best-performing Convolutional Neural Networks (CNNs). The automation process of HPO is characterized by its sizable computational footprint and its lack of…

A significant challenge in nature-inspired algorithmics is the identification of specific characteristics of problems that make them harder (or easier) to solve using specific methods. The hope is that, by identifying these characteristics,…

Performance variability is an important measure for a reliable high performance computing (HPC) system. Performance variability is affected by complicated interactions between numerous factors, such as CPU frequency, the number of…

Grids include heterogeneous resources, which are based on different hardware and software architectures or components. In correspondence with this diversity of the infrastructure, the execution time of any single job, as well as the total…

This non-conventional paper represents the first attempt to uncover a possible vulnerability in some proposals for optical network designs and performance comparisons. While optical network designs and planning lie at the heart of achieving…

The performance of software systems remains a persistent concern in the field of software engineering. While traditional metrics like binary size and execution time have long been focal points for developers, the power consumption concern…

We introduce the hyperparameter search problem in the field of machine learning and discuss its main challenges from an optimization perspective. Machine learning methods attempt to build models that capture some element of interest based…

Bayesian optimization (BO) has recently become more prevalent in protein engineering applications and hence has become a fruitful target of benchmarks. However, current BO comparisons often overlook real-world considerations like risk and…

DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have…

Planning in unstructured environments is challenging -- it relies on sensing, perception, scene reconstruction, and reasoning about various uncertainties. We propose DeepSemanticHPPC, a novel uncertainty-aware hypothesis-based planner for…

Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inefficient, leading to excessive token usage and higher…

In predictive tasks, real-world datasets often present different degrees of imbalanced (i.e., long-tailed or skewed) distributions. While the majority (the head) classes have sufficient samples, the minority (the tail) classes can be…

In a previous work we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for reduced basis through hp-greedy refinement. The approach constructs local reduced bases of…

Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the…

In the exascale era in which application behavior has large power & energy footprints, per-application job-level awareness of such impression is crucial in taking steps towards achieving efficiency goals beyond performance, such as energy…

We present an analysis of landscape features for predicting the performance of multi-objective combinatorial optimization algorithms. We consider features from the recently proposed compressed Pareto Local Optimal Solutions Networks…