One schedule may not suit every workload
Hand-selected temperature schedules can become another set of settings to tune.
Neural Schedule learns the schedule used in the supported annealing workflow.
Learned temperature schedules for annealing through a Fourier neural operator.
THE PRODUCT, IN PRACTICE
The schedule used by an annealing run influences how it explores a problem. Neural Schedule learns temperature schedules rather than relying only on manually selected heuristics. Its README describes a Fourier neural operator and makes a learned-versus-heuristic claim; a customer comparison retains the original workload and budget.
Hand-selected temperature schedules can become another set of settings to tune.
Neural Schedule learns the schedule used in the supported annealing workflow.
A stronger result on development inputs need not carry to new inputs.
Evaluate the learned schedule against the accepted heuristic under the same task and budget.
Training, inference and search contribute to the complete operating cost.
Compare the accepted result and total cost rather than reporting only the schedule-generation step.
A schedule-learning product built around an FNO.
Use the learned schedule in its supported optimization workflow.
Define the inputs and reference schedule used in acceptance.
Retain the task, budget and appropriate result checks in the customer engagement.
A team uses repeated annealing runs and wants to evaluate learned schedules.
Illustrative customer use—not a new benchmark or completed customer deployment.Agree training and evaluation inputs and the reference heuristic.
Run the supported learned-schedule workflow.
Compare held-out quality, compute and checking cost.
“Learned > heuristic” is the README’s claim; no general performance multiplier or cross-domain superiority is asserted here. A learned schedule does not supply an optimality certificate by itself.
No new standalone price is supplied for this product; request a scoped proposal. The platform plans buy qualified workflows and capacity, not a second charge every time a compatible method is selected. Existing bundle inclusions do not expand automatically.
An existing product in the SpinForge portfolio. Request the release, available invocation interfaces and setup for your selected workflow; this publication does not invent executable commands or MCP tool names.
Bring a task, an accepted outcome and the environment in which the product needs to work.
Differentiable annealing that lets a learning workflow backpropagate through optimization.
A self-evolving optimizer that improves its optimization algorithms.
Optimization software for turning a supported decision model into a checked candidate solution, with execution planning included.
Select the capability you need directly or include its compatible role in a qualified platform workflow. Production scope identifies release, environment, capacity and support; a product count is not an entitlement.
Explore monthly plans See the system connectionsUse the software directly or ask us to scope the implementation.
One capability. A connected workflow.
A team to put it into practice.