All Katas - ML Katas

by: newest upvotes saves

Forward-mode vs. Reverse-mode autodiff

this year hard (>1 hr) | vjp autodiff jvp

JAX supports both forward-mode and reverse-mode automatic differentiation. While `grad` uses reverse-mode, you can use `jax.jvp` for forward-mode, which computes Jacobian-vector products....
Custom VJP

this year hard (>1 hr) | autodiff custom_vjp

For some functions, you may want to define a custom vector-Jacobian product (VJP). This can be useful for numerical stability or for implementing algorithms that are not easily expressed in terms...