paper-with-me

홈 › Papers

The Outer Product Structure of Neural Network Derivatives

2018-10-09 · Craig Bakker, Michael J. Henry, Nathan O. Hodas

In this paper, we show that feedforward and recurrent neural networks exhibit an outer product derivative structure but that convolutional neural networks do not. This structure makes it possible to use higher-order information without needing approximations or infeasibly large amounts of memory, and it may also provide insights into the geometry of neural network optima. The ability to easily access these derivatives also suggests a new, geometric approach to regularization. We then discuss how this structure could be used to improve training methods, increase network robustness and generalizability, and inform network compression methods.

📄 PDF Abstract BibTeX arXiv:1810.03798

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

POP Image Fusion - Derivative Domain Image Fusion Without Reintegration

2015-12-01 · ICCV 2015 12 · Graham D. Finlayson, Alex E. Hayes

There are many applications where multiple images are fused to form a single summary greyscale or colour output, including computational photography (e.g. RGB-NIR), diffusion tensor imaging (medical), and remote sensing.…

The Zero-Coupon Rate Model for Derivatives Pricing

2016-06-04 · Xiao Lin

The aim of this paper is to present a dual-term structure model of interest rate derivatives in order to solve the two hardest problems in financial modeling: the exact volatility calibration of the entire swaption matri…

model

Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

2025-05-29 · Fangyikang Wang, Hubery Yin, Shaobin Zhuang, Huminhao Zhu 외

Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into various downstream tasks and theoretical ana…

Speeding-Up Back-Propagation in DNN: Approximate Outer Product with Memory

2021-10-18 · Eduin E. Hernandez, Stefano Rini, Tolga M. Duman

In this paper, an algorithm for approximate evaluation of back-propagation in DNN training is considered, which we term Approximate Outer Product Gradient Descent with Memory (Mem-AOP-GD). The Mem-AOP-GD algorithm implem…

Outer Product-based Neural Collaborative Filtering

2018-08-12 · Xiangnan He, Xiaoyu Du, Xiang Wang, Feng Tian 외

In this work, we contribute a new multi-layer neural network architecture named ONCF to perform collaborative filtering. The idea is to use an outer product to explicitly model the pairwise correlations between the dimen…

Collaborative FilteringMulti-Domain Recommender SystemsRecommendation Systems