OPML: OPtimistic Machine Learning on Blockchain

TL;DR

• We propose OPML (Optimistic Machine Learning), which enables AI model inference and training/fine-tuning on the blockchain system using optimistic approach (OPML is also called FPML, where "FP" refers to fraud proof).
• OPML can provide ML service with low cost and high efficiency compared to ZKML. The participation requirement for OPML is low: We are now able to run OPML with a large language model, e.g., 7B-LLaMA (the model size is around 26GB) on a common PC without GPU.
• OPML adopts a verification game (similar to Truebit and Optimistic Rollup systems) to guarantee decentralized and verifiable consensus on the ML service.
  • The requester first initiates an ML service task.
  • The server then finishes the ML service task and commits results on chain.
  • The verifier will validate the results. Suppose there exists a verifier who declares the results are wrong. It starts a verification game with verification game (dispute game) with the server and tries to disprove the claim by pinpointing one concrete erroneous step.
  • Finally, arbitration about a single step will be conducted on smart contract.
• OPML is still under development, and is open-sourced: OPML-Labs/opml: OPML: OPtimistic Machine Learning on Blockchain (github.com)

Single-Phase Verification Game

The one-phase pinpoint protocol works similarly to referred delegation of computation (RDoC), where two o...