We demonstrate that designing a neural quantum state to be an exact eigenstate of the Hamiltonian's symmetries significantly improves both training speed and final variational energy. For the 2D electron gas, we design TorFormer, a neural network wavefunction which is an exact eigenstate of the total momentum. TorForme...
David D. Dai, Yen-Ting Lin, Marin Soljačić· 0 citations
Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear attention obtains linear-time training and constant-time decoding by compressing history into a fixed-size state. In this work, we ask whether we can connect these regimes...
E. Anand, Abdullah Ateyeh, Archer Wang et al.· 2 citations
The current landscape of AI for physics discovery is reviewed and a critical missing skill is highlighted: the ability to pose the right questions or invent the right principles to guide the development of new theories and the tests to falsify them is highlighted.
M. Shalyt, Nathan Regev, Marin Soljačić et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.