Predict how expert-0's routing share evolves when it already receives 52% of tokens and no load-balancing loss is active.
Same topic, related formats. Practice these next.
Same topic, related formats. Practice these next.
An 8-expert MoE layer trains with top-1 routing and no auxiliary load-balancing loss. After 5k steps the per-expert token fractions are: Expert 0 = 52%, Expert 1 = 31%, Experts 2–7 each under 3%. Expert 0 therefore receives roughly 17× more gradient updates per step than Expert 7. Training continues for another 10k steps with the same data distribution and no balancing regularizer. Predict Expert 0's token fraction at step 15k.
Without load-balancing pressure, Expert 0's 52% share widens past 70% over 10k more steps via the routing-collapse positive feedback loop.
Imagine a tutoring center where one teacher already handles half the students and gets better every week. The leading tutor already teaches half the class and gets better every day. With no rule forcing fair distribution, more students pick the best tutor, who improves even faster. After months, one tutor handles most of the school.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
Everything important, quickly.
7 min: scenario parsing + feedback loop math + prediction calibration + wrong-answer analysis.
Real products, models, and research that use this idea.
What an interviewer would ask next. Try answering before peeking at the approach.
Red flags and common mistakes that signal junior thinking. Click to expand.
Predicting the share stays stable at 52%, that ignores the self-reinforcing gradient asymmetry.
The night-before-the-interview bullets. Scan these on the way to the call.
Primary sources. Skim if you want the original framing.