Papers · Proving inference · SpaGKR
SpaGKR
Sparsity-aware protocol for zk-friendly ML models: Shedding lights on practical ZKML
Reported benchmarks
| model | speedup vs dense zkml | speedup from ternary |
|---|---|---|
| Sparse linear layers | 45 | — |
| Ternary network | — | 5 |
Notes
Two orthogonal wins, both worth separating when plotting: (1) SpaGKR-LS makes proof time scale with the number of NON-ZERO parameters, giving 45x on sparse linear layers; (2) ternary networks give a further ~5x. Relevant to MoE and pruned models.
Quantization, in full
| bits | 1.58 |
|---|---|
| scheme | Ternary networks: parameters restricted to {-1, 0, 1}, which ELIMINATES multiplications entirely |
| accuracy_retention | None |
| speedup_from_quantization | 5.0 |
| note | THE key data point for the quantization question. Ternary quantization alone buys a further ~5x proof-time reduction, on top of the 45x that sparsity-aware linear layers (SpaGKR-LS) buy over sparsity-oblivious ZKML. This is the strongest published evidence that lower bit width => faster proving, and it quantifies the effect. |
Our reading
Citation neighbourhood
Builds on
- none recorded
Cited by, in this corpus
Edges are a proxy: paper A's text mentions B anywhere (body or bibliography). See the full graph.