Skip to content
Log in

Author

Regan McDonald

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Book Open access Aug 2026

Towards Network-Efficient Cross-Regional Inference via Learned Activation Compression

Feather is presented, a system that reduces this overhead by compressing intermediate activations before transmission and reconstructing them before downstream layers resume execution, consistently outperforming existing compression schemes, including linear autoencoder, PCA, and SVD.

Regan McDonald, M. Rego, Ertza Warraich et al. · 0 citations