4 papers
Path convergence in diffusion models
Roi Holtzman, Roman Beauvallet, Werner Krauth
We discuss diffusion-model paths interpolating between a target distribution known only through p patterns and a reference distribution that can be sampled. These interpolating pat…
Hyperparameter Transfer for Dense Associative Memories
Roi Holtzman, Dmitry Krotov, Boris Hanin
Dense Associative Memory (DenseAM) is a promising family of AI architectures that is represented by a neural network performing temporal dynamics on an energy landscape. While hype…
Shortcuts to adiabaticity across a separatrix
Roi Holtzman, Oren Raz, Christopher Jarzynski
Shortcuts to adiabaticity are strategies for conserving adiabatic invariants under non-adiabatic (i.e. fast-driving) conditions. Here, we show how to extend classical, Hamiltonian…
Hamiltonian Memory: An Erasable Classical Bit
Roi Holtzman, Geva Arwas, Oren Raz
Computations implemented on a physical system are fundamentally limited by the laws of physics. A prominent example for a physical law that bounds computations is the Landauer prin…