paper-with-me

Papers

Theory-Inspired Path-Regularized Differential Network Architecture Search

2020-06-30 · NeurIPS 2020 12 · Pan Zhou, Caiming Xiong, Richard Socher, Steven C. H. Hoi

Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g. convolution, skip connection and zero operation, to the network optimization. We prove that the architectures with more skip connections can converge faster than the other candidates, and thus are selected by DARTS. This result, for the first time, theoretically and explicitly reveals the impact of skip connections to fast network optimization and its competitive advantage over other types of operations in DARTS. Then we propose a theory-inspired path-regularized DARTS that consists of two key modules: (i) a differential group-structured sparse binary gate introduced for each operation to avoid unfair competition among operations, and (ii) a path-depth-wise regularization used to incite search exploration for deep architectures that often converge slower than shallow ones as shown in our theory and are not well explored during the search. Experimental results on image classification tasks validate its advantages.

📄 PDF Abstract BibTeX arXiv:2006.16537

Code (1)

salesforce/PR-DARTS pytorch

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

DARTS Differentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with…

Similar Papers 제목 키워드 기반

Differential equation and probability inspired graph neural networks for latent variable learning

2022-02-28 · Zhuangwei Shi

Probabilistic theory and differential equation are powerful tools for the interpretability and guidance of the design of machine learning models, especially for illuminating the mathematical motivation of learning latent…

Stock Predictiontext-classificationText ClassificationVariational Inference

Expressive Power of Randomized Signature

2021-09-27 · NeurIPS Workshop DLDE 2021 12 · Christa Cuchiero, Lukas Gonon, Lyudmila Grigoryeva, Juan-Pablo Ortega 외

We consider the question whether the time evolution of controlled differential equations on general state spaces can be arbitrarily well approximated by (regularized) regressions on features generated themselves through …

compressed sensingLEMMATransfer Learning

Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks

2021-10-18 · NeurIPS 2023 11

Understanding the fundamental principles behind the success of deep neural networks is one of the most important open questions in the current literature. To this end, we study the training problem of deep neural network…

Physics-informed machine learning as a kernel method

2024-02-12 · Nathan Doumèche, Francis Bach, Gérard Biau, Claire Boyer

Physics-informed machine learning combines the expressiveness of data-based approaches with the interpretability of physical models. In this context, we consider a general regression problem where the empirical risk is r…

Physics-informed machine learningregression

Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance

2018-05-30 · NeurIPS 2018 12 · Giulia Luise, Alessandro Rudi, Massimiliano Pontil, Carlo Ciliberto

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein dis…