Moreover, we introduce Optimal Posterior Damage (OPD), a robust pruning criterion that:
⚡ Reuses posterior precision to guide efficient sparsification
⚡ Covers structured & unstructured pruning seamlessly
⚡ Scales well across various architectures and sparsity levels
⚡ Reuses posterior precision to guide efficient sparsification
⚡ Covers structured & unstructured pruning seamlessly
⚡ Scales well across various architectures and sparsity levels
Comments
☝️We showcase significant computational savings while retaining high performance across different sparsity levels:
📈 Achieves up to 20x computational savings with minimal accuracy degradation
📅 Wed, Dec 11 | 11 AM - 2 PM PST
📍 East Exhibit Hall A-C #4110, Vancouver Convention Centre
📄 Or check out the paper here: https://arxiv.org/abs/2402.15978
@bertrand-sharp.bsky.social, and Stephan Günnemann