Research map / Optimization / Optimizers
Adaptive Second Order Coresets for Data-efficient Machine Learning
Omead Pooladzandi, David Davini, Baharan Mirzasoleiman
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 |
|---|---|---|---|
| select weighted coresets using Hessian-preconditioned gradients instead of gradient-only selection | ResNet20 with SGD+Momentum · CIFAR10 | test accuracy: 43.6% ± 1.6 (75%) -> 55.4% ± 1.1 (74%) | Improved |
| select weighted coresets using Hessian-preconditioned gradients instead of random sampling | ResNet20 with AdaHessian · CIFAR10 | test accuracy: 59.1% ± 2.8 (87%) -> 60.2% ± 0.5 (73%) | Improved |
| use AdaCore-selected subsets rather than CRAIG subsets | ResNet18 · Imbalanced CIFAR10, S=1%, R=20 | test accuracy: 48.6% ± 0.8 -> 57.3% ± 0.5 | Improved |
| use AdaCore-selected subsets rather than random subsets | ResNet18 · Imbalanced CIFAR10, S=1%, R=20 | test accuracy: 54.7% ± 0.3 -> 57.3% ± 0.5 | Improved |
| use AdaCore-selected subsets rather than CRAIG subsets | ResNet50 with SGD+Momentum · BDD100k | test accuracy: 72.3% -> 74.3% | Improved |
| remove exponential averaging of gradient and Hessian (ablation) | AdaCore with ResNet20 and AdaHessian · CIFAR10 | test accuracy: 60.2% ± 0.5 -> 58.4% ± 0.2 | Hurt |
| remove exponential averaging of gradient and Hessian (ablation) | AdaCore with ResNet20 and SGD+Momentum · CIFAR10 | test accuracy: 55.4% ± 1.1 -> 51.5% ± 1.1 | Hurt |
| use exponential averaging of gradients only, without Hessian averaging (ablation) | AdaCore with ResNet20 and AdaHessian · CIFAR10 | test accuracy: 60.2% ± 0.5 -> 59.8% ± 0.5 | Hurt |
| use exponential averaging of gradients only, without Hessian averaging (ablation) | AdaCore with ResNet20 and SGD+Momentum · CIFAR10 | test accuracy: 55.4% ± 1.1 -> 53.2% ± 1.1 | Hurt |
| use exponential averaging of Hessian only, without gradient averaging (ablation) | AdaCore with ResNet20 and AdaHessian · CIFAR10 | test accuracy: 60.2% ± 0.5 -> 60.2% ± 0.5 | No clear effect |
| use exponential averaging of Hessian only, without gradient averaging (ablation) | AdaCore with ResNet20 and SGD+Momentum · CIFAR10 | test accuracy: 55.4% ± 1.1 -> 54.4% ± 1.1 | Hurt |
| increase the Hessian-estimation batch size to 512 (ablation) | AdaCore with ResNet20 and AdaHessian · CIFAR10 | test accuracy: 60.2% ± 0.5 -> 57.2% ± 0.5 | Hurt |
Closest papers by meaning
- AutoCoreset: An Automatic Practical Coreset Construction Framework (ICML 2023 · similarity 0.89)
- Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes (NeurIPS 2025 · similarity 0.87)
- Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints (ICML 2024 · similarity 0.87)
- $\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning (ICLR 2024 · similarity 0.85)
- Efficient Core-set Selection for Deep Learning Through Squared Loss Minimization (ICML 2025 · similarity 0.85)
- Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary (ICML 2024 · 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.
