Alistair Letcher
@aletcher.bsky.social
PhD student in Oxford (@flair-ox.bsky.social), working on RL & AI Safety 🤖
Website: aletcher.github.io
Website: aletcher.github.io
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.
- 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.
March 24, 2025 at 4:40 PM
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.
- 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.
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...
March 24, 2025 at 4:39 PM
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...