When Bias Meets Trainability: Connecting Theories of Initialization

arXiv:2505.12096 · cs.LG, cs.AI, stat.ML · Submitted 2025-05-17 · Read on arXiv

cs.LG, cs.AI, stat.ML

Submitted: 2025-05-17

Updated: 2026-02-28

Code: https://github.com/abassi98/igb_and_trainability

Terminology

• Activation Function — 46× in this paper · explained in 1 episode
• Transformer — 19× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Neural Tangent Kernel — 2× in this paper
• Vision Transformer (ViT) — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Loss Function — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Where You Place the Norm Matters: From Prejudiced to Neutral Initializations
• Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs
• Adam: A Method for Stochastic Optimization
• Deep Information Propagation
• Tensor Programs II: Neural Tangent Kernel for Any Architecture
• Dynamical Mean-Field Theory of Self-Attention Neural Networks

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks