4aaa76178f8567e05c8e8295c96171d8-AuthorFeedback.pdf
–Neural Information Processing Systems
Gradient descent: Asillustrated byR1'sexample off(x),ourcorrectness condition forautodiffsystems doesnot12 necessarily imply the correctness of the gradient descent based on those systems (i.e., that the gradient descent13 converges to Clarke critical points). This gives a partial answer to R3's question on possible drawbacks of using14 intensionalderivatives. This is a good question that would lead to interesting future work.
Neural Information Processing Systems
Feb-8-2026, 08:24:40 GMT
- Technology: