Can Training Logs Make Model Comparisons More Precise?

arXiv:2608.02705 · cs.LG, cs.AI, stat.ML · Submitted 2026-08-03 · Read on arXiv

Wei-Jung Huang

cs.LG, cs.AI, stat.ML

Submitted: 2026-08-03

Comments: Accepted at the ICML 2026 Workshop on Hypothesis Testing

Journal ref: The ICML 2026 Workshop on Hypothesis Testing

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 22× in this paper · explained in 1 episode
• Variance Reduction — 12× in this paper · explained in 2 episodes
• Calibration — 8× in this paper · explained in 9 episodes
• Overfitting — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Pairwise Comparisons — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Principal Component Analysis (PCA) — 1× in this paper · explained in 8 episodes
• Robustness — 1× in this paper · explained in 6 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes

Sources

• The Benchmark Lottery
• Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
• Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks