English
Related papers

Related papers: Optimizing Loss Functions Through Multivariate Tay…

200 papers

This paper studies numerical solutions for parameterized partial differential equations (P-PDEs) with deep learning (DL). P-PDEs arise in many important application areas and the computational cost using traditional numerical schemes can be…

Numerical Analysis · Mathematics 2020-11-03 Yuyan Chen , Bin Dong , Jinchao Xu

Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, directly training deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks.…

Artificial Intelligence · Computer Science 2024-04-30 Shijie Chen , Yu Zhang , Qiang Yang

Domain generalization on graphs aims to develop models with robust generalization capabilities, ensuring effective performance on the testing set despite disparities between testing and training distributions. However, existing methods…

Machine Learning · Computer Science 2024-11-21 Qin Tian , Chen Zhao , Minglai Shao , Wenjun Wang , Yujie Lin , Dong Li

In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizability of deep learning, especially in such an over-parametrized…

Disordered Systems and Neural Networks · Physics 2024-09-17 Hao Liao , Wei Zhang , Zhanyi Huang , Zexiao Long , Mingyang Zhou , Xiaoqun Wu , Rui Mao , Chi Ho Yeung

Learned optimizers (LOs) have the potential to significantly reduce the wall-clock training time of neural networks. However, they can struggle to optimize unseen tasks (meta-generalize), especially when training networks wider than those…

Machine Learning · Computer Science 2026-03-20 Benjamin Thérien , Charles-Étienne Joseph , Boris Knyazev , Edouard Oyallon , Irina Rish , Eugene Belilovsky

The success of deep learning has been due, in no small part, to the availability of large annotated datasets. Thus, a major bottleneck in current learning pipelines is the time-consuming human annotation of data. In scenarios where such…

Machine Learning · Computer Science 2021-01-29 Alona Golts , Daniel Freedman , Michael Elad

Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems. However, GNNs on such applications are limited when there are…

Machine Learning · Computer Science 2021-11-09 Debmalya Mandal , Sourav Medya , Brian Uzzi , Charu Aggarwal

This paper investigates the impact of loss function selection in deep unfolding techniques for sparse signal recovery algorithms. Deep unfolding transforms iterative optimization algorithms into trainable lightweight neural networks by…

Signal Processing · Electrical Eng. & Systems 2026-04-24 Koshi Nagahisa , Ryo Hayakawa , Youji Iiguni

Recently, neural networks trained as optimizers under the "learning to learn" or meta-learning framework have been shown to be effective for a broad range of optimization tasks including derivative-free black-box function optimization.…

Machine Learning · Computer Science 2019-10-03 Vishnu TV , Pankaj Malhotra , Jyoti Narwariya , Lovekesh Vig , Gautam Shroff

In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Thanh Vu , Yanqi Zhou , Chunfeng Wen , Yueqi Li , Jan-Michael Frahm

The theory-guided neural network (TgNN) is a kind of method which improves the effectiveness and efficiency of neural network architectures by incorporating scientific knowledge or physical information. Despite its great success, the…

Machine Learning · Computer Science 2022-06-14 Miao Rong , Dongxiao Zhang , Nanzhe Wang

Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust…

Computation and Language · Computer Science 2019-08-29 Zi-Yi Dou , Keyi Yu , Antonios Anastasopoulos

This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures…

Artificial Intelligence · Computer Science 2018-06-11 Jingyi Xu , Zilu Zhang , Tal Friedman , Yitao Liang , Guy Van den Broeck

The significance of learning constraints from data is underscored by its potential applications in real-world problem-solving. While constraints are popular for modeling and solving, the approaches to learning constraints from data remain…

Machine Learning · Computer Science 2024-03-05 Eduardo Vyhmeister , Rocio Paez , Gabriel Gonzalez

This paper investigates reinforcement learning with constraints, which are indispensable in safety-critical environments. To drive the constraint violation monotonically decrease, we take the constraints as Lyapunov functions and impose new…

Machine Learning · Computer Science 2021-05-07 Chuangchuang Sun , Dong-Ki Kim , Jonathan P. How

The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most…

Machine Learning · Computer Science 2020-04-14 Garrett Bingham , William Macke , Risto Miikkulainen

Determining whether deep neural network (DNN) models can reliably recover target functions at overparameterization is a critical yet complex issue in the theory of deep learning. To advance understanding in this area, we introduce a concept…

Machine Learning · Computer Science 2024-06-27 Yaoyu Zhang , Leyang Zhang , Zhongwang Zhang , Zhiwei Bai

Learning with a {\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper,…

Machine Learning · Computer Science 2018-05-22 Yi Xu , Shenghuo Zhu , Sen Yang , Chi Zhang , Rong Jin , Tianbao Yang

Purpose: This work aims at developing a generalizable MRI reconstruction model in the meta-learning framework. The standard benchmarks in meta-learning are challenged by learning on diverse task distributions. The proposed network learns…

Computer Vision and Pattern Recognition · Computer Science 2021-10-05 Wanyu Bian , Yunmei Chen , Xiaojing Ye , Qingchao Zhang

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite…

Machine Learning · Computer Science 2025-04-01 Binchuan Qi , Wei Gong , Li Li