AlexandriaChemistry/ACT

Optimize train_ff to only compute what is being trained on

Open

#902 opened on Aug 13, 2025

View on GitHub
 (0 comments) (0 reactions) (0 assignees)C++ (2 forks)auto 404
enhancementhelp wanted

Repository metrics

Stars
 (17 stars)
PR merge metrics
 (PR metrics pending)

Description

For instance, if we train on the electrostatics, it is not needed to compute the other, potentially expensive energies.

Contributor guide

Research direction
Analyze the train ff function to identify which computational terms (e.g., electrostatics) are needed based on the training targets, then modify the code to conditionally compute only those terms, skipping unnecessary expensive calculations.
Tech stack
cpp
Domain
backendmachine learningperformance
Issue type
Performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
GitC++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60