Students Professional
JA EN

#entropy

4 articles

01 ·Inference & Serving·★ MEMBER·PAPER·11 min read Paper Explained: Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement A third to a half of the teacher's token-level grades are wrong, yet the student improves just as fast either way. This paper traces on-policy distillation's gains not to imitating a teacher but to suppressing the student's own low-probability tokens — and drops the teacher entirely. 02 ·Information Theory·★ MEMBER·PAPER·11 min read Mutual Information — Putting a Number on What You Know How much does knowing one thing shrink your uncertainty about another? Mutual information turns that into a single number. We build it from entropy subtraction, work through conditional MI, the data processing inequality and why estimation is hard, and end at why the InfoNCE loss behind modern contrastive learning is called a lower bound on mutual information. 03 ·Information Theory·FREE·9 min read Entropy and Cross-Entropy — Where the Loss Function Comes From The cross-entropy loss you write in every classifier wasn't handed down by decree. Starting from the idea of surprise, we walk a single path through entropy and cross-entropy to that familiar one-liner — and finish with why squared error is the wrong tool for the job. 04 ·Information Theory·★ MEMBER·9 min read Information Theory and AI — Where Cross-Entropy Loss Came From Information is surprise, entropy is average surprise, KL divergence is the gap between two distributions. Stack those three and the loss function you already use for classification falls out as the only reasonable answer — including why it involves a logarithm, and what perplexity is really counting.