Every time this comes up people say they're not actually useful for ML. Is that true? And if not what would they be useful for
Factoring. Reversing ECC operations. Decrypting all the data thought to be safely stored at rest in any non quantum resistant storage.
I do think ai algorithms could be built that quantum gates could be fast at, but I don’t have any ideas off the top of my head this morning. If you think of AI training as searching the space of computational complexity and quantum algorithms as accessing a superposition of search states I would guess there’s an intersection. Google thinks so too - the lab is called quantum ai.
breaking crypto, for one
No, a true quantum computer will not necessarily solve NP-complete (NPC) problems efficiently. Quantum algorithms like Grover’s provide quadratic speedups, but this is insufficient to turn exponential-time solutions into polynomial-time ones. While quantum computers excel in specific tasks (e.g., Shor’s algorithm for factoring), there’s no evidence they can solve all NP-complete problems efficiently.
Current complexity theory suggests that , the class of problems solvable by quantum computers, does not encompass . Quantum computers may aid in approximations or heuristics for NPC problems but won’t fundamentally resolve them in polynomial time unless , which remains unlikely.