Two slides show how Frank-Wolfe approximates the constraint intersection in BroxGD
peter_richtarik · x · 2026-11-05
Peter Richtarik explains with two slides how Frank-Wolfe (FW) relates to his recently rediscovered Broximal Gradient Descent (BroxGD): FW approximates BroxGD, which itself approximates the Broximal Point Method (BPM), a projection-free sister of proximal/projected gradient descent. The figure shows the approximate ball B̂(x,t)—X shrunk toward x to diameter t—always lies inside the ball B(x,t), touching the sphere at both ends of a diameter, which is how the constraint-ball intersection is approximated in FW.
Related event: KAUST's BroxGD Paper Clarifies Frank-Wolfe as Projection-Free Approximation(3 posts)→
More from Research
- Firecrawl launches Legal Retrieval Benchmark: its index tops 581-request test at 76.2% — devdigest · 2026-11-05
- UW study: leading AI models rate Chinese and Nigerian accents lower in speech scoring — lazowska · 2026-11-05
- Paper asks whether LLMs are rational: coherence norms published in AI journal — peterbhase · 2026-11-05
- The Data Efficiency Gap Between Humans and AI: No System Has Both Targets — dyamins · 2026-11-05
- 0.8B open-source HaloGuard 2.0 claims streaming-guard SOTA, beating models 5-10x its size — const_reborn · 2026-11-05
- Anima Anandkumar to keynote SC26 supercomputing conference in Chicago — AnimaAnandkumar · 2026-11-05