KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches

arXiv:2505.14777 · cs.LG, cs.AI · Submitted 2025-05-20 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-05-20

Updated: 2026-10-06

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Kinetics-inspired Optimizer — 1× in this paper

Sources

• The Prevalence of Neural Collapse in Neural Multivariate Regression
• Qwen Technical Report
• Phase Diagram of Initial Condensation for Two-layer Neural Networks
• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
• RandAugment: Practical automated data augmentation with a reduced search space
• DeepSeek-V3 Technical Report
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
• Sharpness-Aware Minimization for Efficiently Improving Generalization
• Explaining and Harnessing Adversarial Examples
• Deep Residual Learning for Image Recognition
• How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks
• Adam: A Method for Stochastic Optimization
• Decoupled Weight Decay Regularization
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Adding Gradient Noise Improves Learning for Very Deep Networks
• An overview of gradient descent optimization algorithms
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
• ResNet strikes back: An improved training procedure in timm
• HuggingFace's Transformers: State-of-the-art Natural Language Processing

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