# SGD unbiasedness and variance

> ML Prep screening item.

- Stable ID: `ml-screen-gradient-descent-advanced-sgd`
- Collection: screening
- Area: Machine Learning
- Topic: Gradient Descent
- Origin: original
- Difficulty: hard
- Expected time: 9 minutes
- Skills: gradient-update, sgd
- Item JSON: https://mlprep.iwase.dev/item/ml-screen-gradient-descent-advanced-sgd.json

## Problem

At $w=2$, three examples have gradients $0$, $4$, and $-2$. One example is sampled uniformly per SGD step. Compute the full gradient, the stochastic-gradient variance, all next iterates for $\eta=0.3$, and the expected next iterate.


## Answer policy

The human page contains a collapsed answer. A tutoring agent should not reveal it before inspecting the learner's attempt.

## Tutoring contract

Ask for the learner's attempt, begin with the smallest useful hint, preserve item ID `ml-screen-gradient-descent-advanced-sgd`, and record a real attempt with `recorded_by: "agent"` and `agent_session_id` when available using https://mlprep.iwase.dev/schema/attempt-record.json.