Large language models (LLMs) have demonstrated great potential in the financial domain. Thus, it becomes important to assess the performance of LLMs in the financial tasks. In this work, we introduce CFBenchmark, to e...
详细信息
Neural operators have proven to be a promising approach for modeling spatiotemporal systems in the physical sciences. However, training these models for large systems can be quite challenging as they incur significant...
详细信息
Cluster internal evaluation index is used to evaluate and guide the results of clustering, which has been considered as one of the vital issues in the application of clustering. Granular-ball is the multi-granularity ...
Cluster internal evaluation index is used to evaluate and guide the results of clustering, which has been considered as one of the vital issues in the application of clustering. Granular-ball is the multi-granularity characterization of the data set, In this paper, the classic Silhouettes indexes were improved by using granular-ball to represent the grain, we proposed a Silhouettes cluster internal evaluation index based on granular-ball(GSCVI), GSCVI can effectively obtain the optimal number of clusters for arbitrary-shaped and noisy data sets, and it is superior to most of the existing indexes for both artificial and real data sets.
Although deep neural networks have achieved prominent performance on many NLP tasks, they are vulnerable to adversarial examples. We propose Dirichlet Neighborhood Ensemble (DNE), a randomized method for training a ro...
详细信息
In this paper, we present the study of interactional arrangements that support the collaboration of headquarters (HQ), field responders, and a computational planning agent in a time-critical task setting created by a ...
详细信息
Machine Learning (ML) models rely on capturing important feature interactions to generate predictions. This study is focused on validating the hypothesis that model predictions often depend on interactions involving o...
详细信息
ISBN:
(数字)9798350344790
ISBN:
(纸本)9798350344806
Machine Learning (ML) models rely on capturing important feature interactions to generate predictions. This study is focused on validating the hypothesis that model predictions often depend on interactions involving only a few features. This hypothesis is inspired by t-way combinatorial testing for software systems. In our study, we utilize the notion of Shapley Additive Explanations (SHAP) values to quantify each feature’s contribution to model prediction. We then use a greedy approach to identify a minimal subset of features (t) required to determine a model prediction. Our empirical evaluation is performed on three datasets: Adult Income, Mushroom, and Breast Cancer, and three classification models: Logistic Regression, XGBoost, and SVM. Through our experiments, we find that the majority of predictions are determined by interactions involving only a subset of features.
In current scientific workflows, the computational needs of tasks might not be known when it is submitted to a system for execution. Current resource management (RM) systems and workflow managers (WFMs) provide limite...
详细信息
ISBN:
(数字)9798350364606
ISBN:
(纸本)9798350364613
In current scientific workflows, the computational needs of tasks might not be known when it is submitted to a system for execution. Current resource management (RM) systems and workflow managers (WFMs) provide limited support for dynamic resource allocation in HPC systems, thus the common approach is to request the maximum resources needed for a maximum time, potentially wasting resources. However, in some cases, maximum resources may not be estimated a priori, as a result, a workflow may be completed after the deadline, or in cases, the task may terminated by the resource manager. A combination of workflow manager and resource management system that can accommodate a fine-grain elastic resource allocation during the execution of a workflow would alleviate this problem. This paper presents a dynamic elastic resource management framework based on the Parsl workflow manager and PMIx-enabled SLURM and reports the early evaluation of the framework using two workflow applications.
In recent years, black-box distributed optimization (DBO) has been widely studied to solve complex optimization problems in multi-agent systems, such as hyperparameter optimization of distributed machine learning. How...
详细信息
We develop the first end-to-end sample complexity of model-free policy gradient (PG) methods in discrete-time infinite-horizon Kalman filtering. Specifically, we introduce the receding-horizon policy gradient (RHPG-KF...
We develop the first end-to-end sample complexity of model-free policy gradient (PG) methods in discrete-time infinite-horizon Kalman filtering. Specifically, we introduce the receding-horizon policy gradient (RHPG-KF) framework and demonstrate sample complexity for RHPG-KF in learning a stabilizing filter that is ϵ-close to the optimal Kalman filter. Notably, the proposed RHPG-KF framework does not require the system to be open-loop stable nor assume any prior knowledge of a stabilizing filter. Our results shed light on applying model-free PG methods to control a linear dynamical system where the state measurements could be corrupted by statistical noises and other (possibly adversarial) disturbances.
Language-conditioned robot behavior plays a vital role in executing complex tasks by associating human commands or instructions with perception and actions. The ability to compose long-horizon tasks based on unconstra...
详细信息
暂无评论