Learning Under Forgetting: Statistical Support-Selective Retention in Stochastic Training Dynamics
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- Continual Learning and Catastrophic Forgetting
- Scaling Laws for Neural Language Models
- Training Compute-Optimal Large Language Models
- ELLA: Efficient Lifelong Learning for Adapters in Large Language Models
- Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
- A Systematic Review on Long-Tailed Learning
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Omnigrok: Grokking Beyond Algorithmic Data
- Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
- Scaling Data-Constrained Language Models
- Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
- Scaling Laws for Autoregressive Generative Modeling
- 4+3 Phases of Compute-Optimal Neural Scaling Laws
- The Quantization Model of Neural Scaling
- Approaching Deep Learning through the Spectral Dynamics of Weights
- Frequency Regularization: Unveiling the Spectral Inductive Bias of Deep Neural Networks
- A Quantitative Characterization of Forgetting in Post-Training
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