JAX

216 items from n2cholas/awesome-jax ★2,167

Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization. Pranav Subramani, Nicholas… arxiv.org

Uses JAX's JIT and VMAP to achieve faster differentially private than existing libraries.

site link ↗
JAX, M.D.: A Framework for Differentiable Physics. Samuel S. Schoenholz, Ekin D. Cubuk. NeurIPS 2020. arxiv.org

Introduces JAX, M.D., a differentiable physics library which includes simulation environments, interaction potentials, neural networks, and more.

site topic ai topic science link ↗