6/ Huge thanks to my amazing supervisors Stefan Woerner and @zoufalc.bsky.social from @ibm-research.bsky.social Zürich, as well as @mvscerezo.bsky.social and @qzoeholmes.bsky.social for their expertise & feedback along the way :)
24.03.2025 16:42 — 👍 2 🔁 0 💬 0 📌 0
5/ Empirical validation:
- We train a qGAN to learn a challenging 2D Gaussian mixture.
- We observe that global contributions to gradients, while initially small, become significant over training. This challenges the notion that only local observables are viable for training.
24.03.2025 16:39 — 👍 0 🔁 0 💬 1 📌 0
4/ In particular, our results enable us to prove that qGANs -- quantum generators trained with classical discriminators -- avoid barren plateaus, even for arbitrarily deep discriminators. This insight suggests qGANs as a scalable and promising approach for distribution learning.
24.03.2025 16:39 — 👍 0 🔁 0 💬 1 📌 0
3/ Our work provides significantly tighter upper & lower gradient bounds for VQAs, compatible with realistic circuit assumptions & efficiently evaluable with classical resources. This clarifies when & why barren plateaus occur and offers practical tools to design scalable VQAs.
24.03.2025 16:39 — 👍 0 🔁 0 💬 1 📌 0
2/ VQAs are one of the most promising near-term approaches to solving problems in quantum chemistry and black-box optimization, including machine learning. But they often fail to scale because of *barren plateaus*, aka gradients that vanish exponentially in the system size.
24.03.2025 16:39 — 👍 1 🔁 0 💬 1 📌 0
1/ Excited to share my recent work with IBM Research, "Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits"! We prove stronger, more realistic, and classically computable gradient bounds for variational quantum algorithms (VQAs). Link: quantum-journal.org/papers/q-202...
24.03.2025 16:39 — 👍 3 🔁 0 💬 1 📌 0
Alistair Letcher, Stefan Woerner, Christa Zoufal
Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
https://arxiv.org/abs/2309.12681
20.09.2024 07:31 — 👍 0 🔁 1 💬 0 📌 0
