DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)· 2023
Inline Hardware KV-Cache Compression for Long-Context Transformer Inference: An Architectural Case for a Memory-Path Compression Engine
- 77,000citations
- 2023year
Short summary
This paper presents an AI/TP system that automatically proves a significant portion of Mizar theorems, achieving 60% in a hammer setting and 75% when guided by human-selected premises.
AI-generated from the title and abstract; the full text is not read.
Key points
- AI/TP system automatically proves ~60% of Mizar theorems in a hammer setting.
- Proof success rate increases to 75% when guided by human-selected premises.
- System integrates E and Vampire provers with learning modifications (ENIGMA, Deepire).
- An incremental loop trains AI/TP systems on millions of ATP proofs.
AI-generated from the title and abstract; the full text is not read.
Abstract
As a present to Mizar on its 50th anniversary, we develop an AI/TP system that automatically proves about 60% of the Mizar theorems in the hammer setting. We also automatically prove 75% of the Mizar theorems when the automated provers are helped by using only the premises used in the human-written Mizar proofs. We describe the methods and large-scale experiments leading to these results. This includes in particular the E and Vampire provers, their ENIGMA and Deepire learning modifications, a number of learning-based premise selection methods, and the incremental loop that interleaves growing a corpus of millions of ATP proofs with training increasingly strong AI/TP systems on them. We also present a selection of Mizar problems that were proved automatically.
The authors' abstract, as published at the source. DROPS (Schloss Dagstuhl – Leibniz Center for Informatics), 2023 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science