AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

LSH-SMILE: Locality Sensitive Hashing Accelerated Simulation and Learning

Chonghao Sima, Yexiang Xue

NeurIPS 2021 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed operator learning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use LSH-SMILE instead of brute-force Torch forward simulationGrain growth simulation · Grain growth simulationruntime (hr): 16.84 -> 3.86Improved
Use LSH-SMILE instead of brute-force Torch forward simulationNanovoid simulation · Nanovoid simulationruntime (hr): 53.13 -> 2.13Improved
Use LSH-SMILE inside backward learningGrain growth learning · Grain growth learningruntime (hr): 17.29 -> 4.5Improved
Use LSH-SMILE for grain growth simulationGrain growth simulation · Grain growth simulationmemory usage (MB): 1135 -> 870Improved
Use LSH-SMILE for nanovoid simulationNanovoid simulation · Nanovoid simulationmemory usage (MB): 3294 -> 2735Improved
Use LSH-SMILE for grain growth learningGrain growth learning · Grain growth learningmemory usage (MB): 1212 -> 889Improved
Replace exact computation with LSH approximationGrain growth simulation · Grain growth simulationdifference from ground truth: 10−5 after 180 stepsNo clear effect
Replace exact computation with LSH approximationNanovoid simulation · Nanovoid simulationdifference from ground truth: 10−5 after 100 stepsNo clear effect
Longer embedded forward simulation in learning (T=30 vs T=10), enabled by LSH-SMILE savingsGrain growth learning · Grain growth learninglearned parameter B (true 1.0): 8.8226 -> 2.01454Improved
Longer embedded forward simulation in learning (T=30 vs T=10)Grain growth learning · Grain growth learninglearned kappa (true 0.1): 0.8431 -> 0.0834962Improved
Longer embedded forward simulation in learning (T=30 vs T=10)Grain growth learning · Grain growth learninglearned parameter A (true 1.0): 1.9431 -> 1.98483Mixed
Longer embedded forward simulation in learning (T=30 vs T=10)Grain growth learning · Grain growth learninglearned parameter L (true 5.0): 9.0462 -> 11.6504Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy