Name
Abstract | ||
|---|---|---|
We present a systematic weight pruning framework of deep neural networks (DNNs) using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a constrained nonconvex optimization problem, and then adopt the ADMM framework for systematic weight pruning. We show that ADMM is highly suitable for weight pruning due to the computational efficiency it offers. We achieve a much higher compression ratio compared with prior work while maintaining the same test accuracy, together with a faster convergence rate. |
Year | Venue | Field |
|---|---|---|
2018 | ICLR | Mathematical optimization,Compression ratio,Rate of convergence,Optimization problem,Mathematics,Deep neural networks,Pruning |
DocType | Volume | Citations |
Journal | abs/1802.05747 | 1 |
PageRank | References | Authors |
0.35 | 7 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tianyun Zhang | 1 | 31 | 6.42 |
| Shaokai Ye | 2 | 38 | 6.53 |
| Yipeng Zhang | 3 | 33 | 8.04 |
| Yanzhi Wang | 4 | 1082 | 136.11 |
| Makan Fardad | 5 | 11 | 1.70 |