#gradient-methods News & Analysis

3 articles tagged with #gradient-methods. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBullisharXiv – CS AI · Mar 176/10

🧠

From $\boldsymbol{\log\pi}$ to $\boldsymbol{\pi}$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight

Researchers introduce Decoupled Gradient Policy Optimization (DGPO), a new reinforcement learning method that improves large language model training by using probability gradients instead of log-probability gradients. The technique addresses instability issues in current methods while maintaining exploration capabilities, showing superior performance across mathematical benchmarks.

AIBullisharXiv – CS AI · Mar 166/10

🧠

MetaKE: Meta-learning Aligned Knowledge Editing via Bi-level Optimization

Researchers propose MetaKE, a new framework for knowledge editing in Large Language Models that addresses the 'Semantic-Execution Disconnect' through bi-level optimization. The method treats edit targets as learnable parameters and uses a Structural Gradient Proxy to align edits with the model's feasible manifold, showing significant improvements over existing approaches.

AINeutralarXiv – CS AI · Mar 264/10

🧠

No Single Metric Tells the Whole Story: A Multi-Dimensional Evaluation Framework for Uncertainty Attributions

Researchers propose a new framework for evaluating uncertainty attribution methods in explainable AI, addressing inconsistent evaluation practices in the field. The study introduces five key properties including a new 'conveyance' metric and demonstrates that gradient-based methods outperform perturbation-based approaches across multiple evaluation criteria.