Boldly go where Gradient Descent has never gone before with DiscoGrad
Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool for automatic differentiation through C++ programs involving input-dependent control flow (e.g., "if (f(x) < c) { ... }", differentiating wrt. x) and randomness. Our initial motivation was to enable the use of gradient descent with simulations, which often rely heavily on such discrete branching. The latter makes plain autodiff mostly useless, since it can only account for the…
In plain words
DiscoGrad is an automatic differentiation tool for C++ programs that contain input-dependent branching and randomness. It enables gradient descent optimization through simulations and complex programs where traditional autodiff fails, by accounting for multiple execution paths rather than just the single path taken. The tool is designed for researchers combining discrete control flow with neural networks for end-to-end training and for optimizing simulations that rely heavily on conditional logic.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool for automatic differentiation through C++ programs involving input-dependent control flow (e.g., "if (f(x) < c) { ... }", differentiating wrt. x) and randomness. Our initial motivation was to enable the use of gradient descent with simulations, which often rely heavily on such discrete branching. The latter makes plain autodiff mostly useless, since it can only account for the single path taken through the program. Our tool offers several backends that handle this situation, giving useful descent directions for optimization by accounting for alternative branches. Besides simulations, this problem arises in many other places, for example in deep learning when trying to combine imperative programs with neural networks. In a nutshell, DiscoGrad applies an (LLVM-based) source-to-source transformation to your C++ program, adding some calls to our header library, which then handles the gradient computation. What sets it apart from similar tools/estimators is that it's fully automatic (no need to come up with a differentiable problem formulation/reparametrization) and that the branching condition can be any function of the program inputs (no need to know upfront what distribution the condition follows). We're currently a team of two working on DiscoGrad as part of a research project, so don't expect to see production-grade code quality, but we do intend for it to be more than a throwaway research prototype. Use cases we've successfully tested include calibrating simulation models of epidemics or evacuation scenarios via gradient descent, and combining simulations with neural networks in an end-to-end trainable fashion. We hope you find this interesting and useful, and we're happy to answer questions!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
