Ziming Liu maps loss-spike phase diagram, shows quadratic model misreads training spikes
ZimingLiu11 · x · 2026-11-01
Ziming Liu's team summarizes their loss-spike study: (1) a phase diagram in the (beta1, beta2) plane gives practical guidance for avoiding spikes; (2) the quadratic landscape model is seriously wrong — 1D slices reveal a core-wall-rollover three-phase landscape that better matches real training and could guide optimizer design.
More from Research
- Paperclip builds biomedical datasets in one shot, cutting months-long curation to about a minute — james_y_zou · 2026-11-04
- Embodied Agent Arena: Closed-Weight VLMs Lead All Five Robot Task Domains, Open-Weight Models Lag — Haojian Huang · 2026-11-04
- FPT University Paper Shows RAG Improves Stock Market Information Retrieval Accuracy and Latency — Huan Phong Thai · 2026-11-04
- Alibaba's adaptive GUI agent training cuts environment interactions by 56-61% — Yuxiang Chai · 2026-11-04
- Large-Scale Study: AI Reviewers Often Ignore How Much You Improved Your Paper — umd-zhou-lab · 2026-11-04
- Kling Team's report: video generation bottleneck shifts from rendering to semantic control — KlingTeam · 2026-11-04