paper-with-me

홈 › Papers

Provable Methods for Training Neural Networks with Sparse Connectivity

2014-12-08 · Hanie Sedghi, Anima Anandkumar

We provide novel guaranteed approaches for training feedforward neural networks with sparse connectivity. We leverage on the techniques developed previously for learning linear networks and show that they can also be effectively adopted to learn non-linear networks. We operate on the moments involving label and the score function of the input, and show that their factorization provably yields the weight matrix of the first layer of a deep network under mild conditions. In practice, the output of our method can be employed as effective initializers for gradient descent.

📄 PDF Abstract BibTeX arXiv:1412.2693

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Provable Subspace Clustering: When LRR meets SSC

2013-12-01 · NeurIPS 2013 12 · Yu-Xiang Wang, Huan Xu, Chenlei Leng

Sparse Subspace Clustering (SSC) and Low-Rank Representation (LRR) are both considered as the state-of-the-art methods for {\em subspace clustering}. The two methods are fundamentally similar in that both are convex opti…

Clustering

Provable Self-Representation Based Outlier Detection in a Union of Subspaces

2017-04-12 · CVPR 2017 7 · Chong You, Daniel P. Robinson, René Vidal

Many computer vision tasks involve processing large amounts of data contaminated by outliers, which need to be detected and rejected. While outlier detection methods based on robust statistics have existed for decades, o…

Outlier Detection

Optimizer-Induced Mode Connectivity: From AdamW to Muon

2026-05-11 · Fangzhao Zhang, Sungyoon Kim, Erica Zhang, Yiqi Jiang 외 arxiv

Mode connectivity has been widely studied, yet the role of the optimizer remains underexplored. We revisit it through optimizer-induced implicit regularization, asking how connectivity behaves when restricted to solution…

Asymptotic properties of one-layer artificial neural networks with sparse connectivity

2021-12-01 · Christian Hirsch, Matthias Neumann, Volker Schmidt

A law of large numbers for the empirical distribution of parameters of a one-layer artificial neural networks with sparse connectivity is derived for a simultaneously increasing number of both, neurons and training itera…

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

2025-10-20 · Hoang Pham, The-Anh Ta, Tom Jacobs, Rebekka Burkholz 외 arxiv

Sparse neural networks promise efficiency, yet training them effectively remains a fundamental challenge. Despite advances in pruning methods that create sparse architectures, understanding why some sparse structures are…

Network Pruning