Research map / Architectures and efficiency / Pruning and efficient tuning
AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning
Krishnateja Killamsetty, Guttu Sai Abhishek, Aakriti Lnu, Ganesh Ramakrishnan, Alexandre V. Evfimievski, Lucian Popa, Rishabh K Iyer
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 gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · SST5 (TPE, Hyperband) | speedup: 9.8× | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · SST5 (TPE, Hyperband) | relative test performance: 2.8% | Hurt |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · SST5 (TPE, Hyperband) | speedup: 7.35× | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · SST5 (TPE, Hyperband) | relative test performance: 0.9% | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · TREC6 (TPE, ASHA) | speedup: 3.15× | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · TREC6 (TPE, ASHA) | relative test performance: 3.4% | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · TREC6 (TPE, ASHA) | speedup: 2.68× | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · TREC6 (TPE, ASHA) | relative test performance: 4.6% | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · CIFAR10 (Random, Hyperband) | speedup: 15× | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · CIFAR10 (Random, Hyperband) | relative test performance: $0.65\%$ | Hurt |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · CIFAR10 (Random, Hyperband) | speedup: 8.7× | Improved |
| Use gradient-based data subsets instead of full-data configuration evaluation | AUTOMATA · CIFAR10 (Random, Hyperband) | relative test performance: $0.14\%$ | Hurt |
Closest papers by meaning
- Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters (ICML 2016 · similarity 0.89)
- Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions (ICLR 2019 · similarity 0.87)
- Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function (NeurIPS 2025 · similarity 0.86)
- On the Parameterization of Second-Order Optimization Effective towards the Infinite Width (ICLR 2024 · similarity 0.86)
- Principled Architecture-aware Scaling of Hyperparameters (ICLR 2024 · similarity 0.85)
- Faster Parameter-Efficient Tuning with Token Redundancy Reduction (CVPR 2025 · similarity 0.84)
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.
