paper-with-me

Papers

On the Landscape of Sparse Linear Networks

2021-01-01 · Dachao Lin, Ruoyu Sun, Zhihua Zhang

Network pruning, or sparse network has a long history and practical significance in modern applications. Although the loss functions of neural networks may yield bad landscape due to non-convexity, we focus on linear activation which already owes benign landscape. With no unrealistic assumption, we conclude the following statements for the squared loss objective of general sparse linear neural networks: 1) every local minimum is a global minimum for scalar output with any sparse structure, or non-intersected sparse first layer and dense other layers with orthogonal training data; 2) sparse linear networks have sub-optimal local-min for only sparse first layer due to low rank constraint, or output larger than three dimensions due to the global minimum of a sub-network. Overall, sparsity breaks the normal structure, cutting out the decreasing path in original fully-connected networks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Similar Papers 제목 키워드 기반

On the Landscape of One-hidden-layer Sparse Networks and Beyond

2020-09-16 · Dachao Lin, Ruoyu Sun, Zhihua Zhang

Sparse neural networks have received increasing interest due to their small size compared to dense networks. Nevertheless, most existing works on neural network theory have focused on dense neural networks, and the under…

Network Pruning

Essentially No Barriers in Neural Network Energy Landscape

2018-03-02 · ICML 2018 7 · Felix Draxler, Kambis Veschgini, Manfred Salmhofer, Fred A. Hamprecht

Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous…

Linear Mode Connectivity in Sparse Neural Networks

2023-10-28 · Luke McDermott, Daniel Cummings

With the rise in interest of sparse neural networks, we study how neural network pruning with synthetic data leads to sparse networks with unique training properties. We find that distilled data, a synthetic summarizatio…

Dataset DistillationLinear Mode ConnectivityNetwork Pruning

SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning

2026-02-03 · Yao-Hui Li, Zeyu Wang, Xin Li, Wei Pang 외 arxiv

Model-based reinforcement learning (MBRL) is sample-efficient but struggles in sparse reward settings. A critical bottleneck arises from the lack of informative gradients in sparse settings, where standard reward models …

Reinforcement Learning

The Difficulty of Training Sparse Neural Networks

2019-06-25 · ICML Workshop Deep_Phenomen 2019 6 · Utku Evci, Fabian Pedregosa, Aidan Gomez, Erich Elsen

We investigate the difficulties of training sparse neural networks and make new observations about optimization dynamics and the energy landscape within the sparse regime. Recent work of \citep{Gale2019, Liu2018} has sho…