Fast and General Automatic Differentiation for Finite-State Methods
cs.FL, cs.AI
Submitted: 2026-02-11
Updated: 2026-11-06
Code: https://github.com/JuliaDiff/ChainRules
Terminology
Sources
- Sequence Transduction with Recurrent Neural Networks
- Differentiable Weighted Finite-State Transducers
- Don't Unroll Adjoint: Differentiating SSA-Form Programs
Related papers
- Quantitative Verification of Infinite-State Networks
- A Unary-to-Nonunary Transition in the Accepting-State Spectrum of Right Quotient for Permutation Automata
- Positive-Data Learning of Fixed-Observation Linear MCFGs from Working Binary Presentations
- On the Separability Problem of VASS Reachability Languages
- Exact Accepting-State Spectrum for Reversal of Permutation Automata
- An exact compress-with-another threshold in a binary automaton family