Research map / Architectures and efficiency / Neural architecture search
Tensor Program Optimization with Probabilistic Programs
Junru Shao, Xiyou Zhou, Siyuan Feng, Bohan Hou, Ruihang Lai, Hongyi Jin, Wuwei Lin, Masahiro Masuda, Cody Hao Yu, Tianqi Chen
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use MetaSchedule to reproduce Ansor’s search space | Tensor program tuning · ResNet-50 | tuning time: 287.17 -> 220.66 min | Improved |
| Use MetaSchedule to reproduce Ansor’s search space | Tensor program tuning · BERT-base | tuning time: 292.45 -> 288.4644 min | Improved |
| Use MetaSchedule to reproduce Ansor’s search space | Tensor program tuning · MobileNet-v2 | tuning time: 280.53 -> 251.8831 min | Improved |
| Use MetaSchedule to reproduce Ansor’s search space | Tensor program tuning · GPT-2 | tuning time: 270.97 -> 214.1358 min | Improved |
| Use MetaSchedule to reproduce Ansor’s search space | Tensor program tuning · Inception-v1 | tuning time: 295.766 -> 290.3632 min | Improved |
| Compose the Use-Tensor-Core module with the existing search space (ablation) | MetaSchedule · BERT-Large workloads | speedup over TVM (AutoTVM): 48% speedup | Improved |
| Progressively compose additional transformation modules (ablation) | MetaSchedule · fused-dense subgraph | performance | Improved |
Closest papers by meaning
- Simple, Distributed, and Accelerated Probabilistic Programming (NeurIPS 2018 · similarity 0.88)
- Synergistic Tensor and Pipeline Parallelism (NeurIPS 2025 · similarity 0.84)
- MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters (ICML 2025 · similarity 0.83)
- tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs) (ICML 2024 · similarity 0.83)
- A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetics (NeurIPS 2024 · similarity 0.83)
- Tensorion: A Tensor-Aware Generalization of the Muon Optimizer (NeurIPS 2026 · similarity 0.83)
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.
