Research map / Architectures and efficiency / RNNs and normalization
FrugalML: How to use ML Prediction APIs more accurately and cheaply
Lingjiao Chen, Matei Zaharia, James Y Zou
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 adaptive API selection to match the best commercial API's accuracy | FrugalML · FER+ | cost: 10 -> 3.3; 67% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · RAFDB | cost: 10 -> 4.3; 57% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · EXPW | cost: 10 -> 5.0; 50% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · AFFECTNET | cost: 10 -> 4.7; 53% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · YELP | cost: 2.5 -> 1.9; 24% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · SHOP | cost: 3.5 -> 1.9; 46% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · IMDB | cost: 2.5 -> 1.9; 24% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · WAIMAI | cost: 3.5 -> 1.4; 60% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · DIGIT | cost: 41 -> 23; 44% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · COMMAND | cost: 41 -> 15; 63% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · FLUENT | cost: 41 -> 26; 37% saved | Improved |
| Use adaptive API selection to match the best commercial API's accuracy | FrugalML · AUDIOMNIST | cost: 41 -> 3.9; 90% saved | Improved |
Closest papers by meaning
- FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training (ICML 2025 · similarity 0.80)
- Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data (ICLR 2025 · similarity 0.80)
- Algorithms with Calibrated Machine Learning Predictions (ICML 2025 · similarity 0.80)
- MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters (ICML 2025 · similarity 0.79)
- Data Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance (AAAI 2024 · similarity 0.79)
- Online Algorithms with Uncertainty-Quantified Predictions (ICML 2024 · similarity 0.79)
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.
