We introduce a general formulation for automatic differentiation through direct form filters, yielding a closed-form backpropagation that includes initial condition gradients. The result is a single expression that can represent both the filter and its gradients computation while supporting parallelism. C++/CUDA implementations in PyTorch achieve at least 1000x speedup over naive Python implementations and consistently run fastest on the GPU. For the low-order filters commonly used in practice, exact time-domain filtering with analytical gradients outperforms the frequency-domain method in terms of speed. The source code is available at https://github.com/yoyolicoris/philtorch.
Accelerating Automatic Differentiation of Direct Form Digital Filters
A formulation for automatic differentiation through direct form filters provides a closed-form backpropagation that includes initial condition gradients, achieving significant speedup in time-domain filtering compared to frequency-domain methods.
- Year
- 2025
- Venue
- arXiv 2025
- Authors
- 2
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2511.14390ARXIV-DEFAULT
- TL;DR
- Semantic Scholar