CAPSkip: Cancellation-Aware Prefix Skipping for Selective Backpropagation
cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 14 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Negative Result on Gradient Matching for Selective Backprop
- K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)
- Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning
- Efficient Per-Example Gradient Computations
- Accelerating Deep Learning by Focusing on the Biggest Losers
- Online Batch Selection for Faster Training of Neural Networks
- LESSER: Post-Training Data Selection with Output-Layer Gradients
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis