Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Sep 201819922001200920182026
2 results for “subderivatives”
Provably Correct Automatic Subdifferentiation for Qualified Programsmath.OC

This work shows how to compute subderivatives efficiently without errors.

problem Inefficient and incorrect computation of subderivatives in ML libraries.
method Developed a method to compute provably correct generalized subderivatives at a cost close to the function itself.
result Provable correct generalized subderivatives can be computed at a cost within a factor of 6 of the function itself.
subderivativessubgradientprovably correctML librariesnonlinear programming
2018-09-23abs ↗pdf ↗
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameterscs.LG

Study shows AD for neural nets with machine-representable numbers can be incorrect.

problem Correctness of AD for neural nets with machine-representable numbers.
method Analyzed two sets of parameters: incorrect and non-differentiable. Proved bounds and conditions for AD correctness.
result AD can be incorrect for machine-representable numbers, but provides a Clarke subderivative on non-differentiable set.
automatic differentiationneural networksmachine-representable numbersClarke subderivativedifferentiability
2023-01-31abs ↗pdf ↗