LUMOS: Democratizing SciML Workflows with L0-Regularized Learning for Unified Feature and Parameter Adaptation

TL;DR

LUMOS is a unified framework that uses L0-regularized learning to automatically select features and prune model parameters, simplifying SciML model design and improving efficiency across diverse scientific domains.

Contribution

LUMOS introduces a novel end-to-end approach combining feature selection and model pruning via L0-regularization, reducing manual tuning in SciML workflows.

Findings

Achieves 71.45% parameter reduction

Provides 6.4x inference speedup

Demonstrates effectiveness across 13 SciML workloads

Abstract

The rapid growth of scientific machine learning (SciML) has accelerated discovery across diverse domains, yet designing effective SciML models remains a challenging task. In practice, building such models often requires substantial prior knowledge and manual expertise, particularly in determining which input features to use and how large the model should be. We introduce LUMOS, an end-to-end framework based on L0-regularized learning that unifies feature selection and model pruning to democratize SciML model design. By employing semi-stochastic gating and reparameterization techniques, LUMOS dynamically selects informative features and prunes redundant parameters during training, reducing the reliance on manual tuning while maintaining predictive accuracy. We evaluate LUMOS across 13 diverse SciML workloads, including cosmology and molecular sciences, and demonstrate its effectiveness and generalizability. Experiments on 13 SciML models show that LUMOS achieves 71.45% parameter reduction and a 6.4x inference speedup on average. Furthermore, Distributed Data Parallel (DDP) training on up to eight GPUs confirms the scalability of