# Why Random Pruning Is All We Need to Start Sparse Source: [Why Random Pruning Is All We Need to Start Sparse]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:23:24.960Z Authors: Advait Gadhikar, Sohom Mukherjee, Rebekka Burkholz Published: 2022-10-05T17:34:04.000Z ## Abstract Random masks define surprisingly effective sparse neural network models, as has been shown empirically. The resulting sparse networks can often compete with dense architectures and state-of-the-art lottery ticket pruning algorithms, even though they do not rely on computationally expensive prune-train iterations and can be drawn initially without significant computational overhead. We offer a theoretical explanation of how random masks can approximate arbitrary target networks if they are wider by a logarithmic factor in the inverse sparsity $1 / \\log(1/\\text{sparsity})$. This overparameterization factor is necessary at least for 3-layer random networks, which elucidates the observed degrading performance of random networks at higher sparsity. At moderate to high sparsity levels, however, our results imply that sparser networks are contained within random source networks so that any dense-to-sparse training scheme can be turned into a computationally more efficient sparse-to-sparse one by constraining the search to a fixed random mask. We demonstrate the feasibility of this approach in experiments for different pruning methods and propose particularly effective choices of initial layer-wise sparsity ratios of the random source network. As a special case, we show theoretically and experimentally that random source networks also contain strong lottery tickets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet sub-tasks S4-S6 (25 classes)](): Image Classification; ImageNet sub-tasks S4-S6 (25 classes); Accuracy (S4/25): 94.48. - [Image Classification on ImageNet sub-tasks S1-S3 (10 classes)](): Image Classification; ImageNet sub-tasks S1-S3 (10 classes); Accuracy (S1/10): 94.8. - [Image Classification on ImageNet sub-tasks S7-S9 (50 classes)](): Image Classification; ImageNet sub-tasks S7-S9 (50 classes); Accuracy (S7/50): 92.64. ## Original sources and implementation [Original paper]() [PDF]()