English
Related papers

Related papers: HyperNet Fields: Efficiently Training Hypernetwork…

200 papers

Achieving state-of-the-art performance on natural language understanding tasks typically relies on fine-tuning a fresh model for every task. Consequently, this approach leads to a higher overall parameter cost, along with higher technical…

Computation and Language · Computer Science 2020-07-14 Yi Tay , Zhe Zhao , Dara Bahri , Donald Metzler , Da-Cheng Juan

Linear networks provide valuable insights into the workings of neural networks in general. This paper identifies conditions under which the gradient flow provably trains a linear network, in spite of the non-strict saddle points present in…

Optimization and Control · Mathematics 2020-06-30 Armin Eftekhari

At the heart of deep learning we aim to use neural networks as function approximators - training them to produce outputs from inputs in emulation of a ground truth function or data creation process. In many cases we only have access to…

Machine Learning · Computer Science 2017-07-27 Wojciech Marian Czarnecki , Simon Osindero , Max Jaderberg , Grzegorz Świrszcz , Razvan Pascanu

Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of…

Machine Learning · Computer Science 2023-07-04 Gal Kaplun , Andrey Gurevich , Tal Swisa , Mazor David , Shai Shalev-Shwartz , Eran Malach

Deep neural networks have gained tremendous importance in many computer vision tasks. However, their power comes at the cost of large amounts of annotated data required for supervised training. In this work we review and compare different…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Viktor Seib , Benjamin Lange , Stefan Wirtz

Recent work has shown that convolutional neural networks (CNNs) can be used to estimate optical flow with high quality and fast runtime. This makes them preferable for real-world applications. However, such networks require very large…

Computer Vision and Pattern Recognition · Computer Science 2018-08-21 Osama Makansi , Eddy Ilg , Thomas Brox

Implicit Neural Representations (INRs) have emerged and shown their benefits over discrete representations in recent years. However, fitting an INR to the given observations usually requires optimization with gradient descent from scratch,…

Machine Learning · Computer Science 2022-08-08 Yinbo Chen , Xiaolong Wang

Neural networks have seen an explosion of usage and research in the past decade, particularly within the domains of computer vision and natural language processing. However, only recently have advancements in neural networks yielded…

Machine Learning · Computer Science 2022-07-20 Jacob Renn , Ian Sotnek , Benjamin Harvey , Brian Caffo

In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Arghya Pal , Vineeth N Balasubramanian

Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and…

Machine Learning · Computer Science 2017-03-28 Sek Chai , Aswin Raghavan , David Zhang , Mohamed Amer , Tim Shields

In this work we propose a HyperTransformer, a Transformer-based model for supervised and semi-supervised few-shot learning that generates weights of a convolutional neural network (CNN) directly from support samples. Since the dependence of…

Machine Learning · Computer Science 2022-07-15 Andrey Zhmoginov , Mark Sandler , Max Vladymyrov

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jinhee Kim , Jae Jun An , Kang Eun Jeon , Jong Hwan Ko

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

Complex network theory has been used to study complex systems. However, many real-life systems involve multiple kinds of objects . They can't be described by simple graphs. In order to provide complete information of these systems, we…

Physics and Society · Physics 2015-11-10 Jin-Li Guo , Xin-Yun Zhu

We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independent layer-wise compressions. We show how to efficiently…

Computer Vision and Pattern Recognition · Computer Science 2022-05-23 Maxwell Horton , Yanzi Jin , Ali Farhadi , Mohammad Rastegari

This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get…

Computer Vision and Pattern Recognition · Computer Science 2021-06-05 Bohan Zhuang , Chunhua Shen , Mingkui Tan , Lingqiao Liu , Ian Reid

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many…

Machine Learning · Computer Science 2025-03-07 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

Neural networks based on metric recognition methods have a strictly determined architecture. Number of neurons, connections, as well as weights and thresholds values are calculated analytically, based on the initial conditions of tasks:…

Neural and Evolutionary Computing · Computer Science 2025-06-10 Polad Geidarov

This work examines the deep disconnect between existing theoretical analyses of gradient-based algorithms and the practice of training deep neural networks. Specifically, we provide numerical evidence that in large-scale neural network…

Machine Learning · Computer Science 2022-06-20 Jingzhao Zhang , Haochuan Li , Suvrit Sra , Ali Jadbabaie

Employing deep neural networks as natural image priors to solve inverse problems either requires large amounts of data to sufficiently train expressive generative models or can succeed with no data via untrained neural networks. However,…

Machine Learning · Computer Science 2019-10-25 Oscar Leong , Wesam Sakla