Timezone: »

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
Mao Ye · Lemeng Wu · Qiang Liu

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #294

Despite the great success of deep learning, recent works show that large deep neural networks are often highly redundant and can be significantly reduced in size. However, the theoretical question of how much we can prune a neural network given a specified tolerance of accuracy drop is still open. This paper provides one answer to this question by proposing a greedy optimization based pruning method. The proposed method has the guarantee that the discrepancy between the pruned network and the original network decays with exponentially fast rate w.r.t. the size of the pruned network, under weak assumptions that apply for most practical settings. Empirically, our method improves prior arts on pruning various network architectures including ResNet, MobilenetV2/V3 on ImageNet.

Author Information

Mao Ye (The University of Texas at Austin)
Lemeng Wu (UT Austin)
Qiang Liu (UT Austin)

More from the Same Authors