quiz.json

[
  {
    "question": "What problem does momentum solve in gradient descent?",
    "options": ["It reduces memory usage", "It dampens oscillation by accumulating past gradients, accelerating movement in consistent directions", "It eliminates the need for a learning rate", "It prevents overfitting"],
    "correct": 1,
    "explanation": "In narrow valleys, gradients oscillate across the valley while making slow progress along it. Momentum accumulates past gradients: consistent directions amplify while oscillating directions cancel, giving smoother, faster convergence.",
    "stage": "pre"
  },
  {
    "question": "What is the key difference between Adam and AdamW?",
    "options": ["AdamW uses a higher learning rate", "AdamW applies weight decay directly to weights instead of through the gradient, giving proper regularization", "AdamW doesn't use momentum", "AdamW only works with transformers"],
    "correct": 1,
    "explanation": "In Adam + L2, the adaptive learning rate scales the regularization term differently per parameter. AdamW decouples weight decay from the gradient update, applying uniform shrinkage regardless of gradient statistics.",
    "stage": "pre"
  },
  {
    "question": "Why does Adam use bias correction in early training steps?",
    "options": ["To prevent overfitting", "The moment estimates are initialized to zero, so early values are biased toward zero; correction compensates for this cold start", "To clip large gradients", "To speed up convergence"],
    "correct": 1,
    "explanation": "At step 1 with beta1=0.9, m_1 = 0.1 * gradient (10x too small). Dividing by (1 - 0.9^1) = 0.1 corrects this to the actual gradient. The correction becomes negligible after ~50 steps.",
    "stage": "post"
  },
  {
    "question": "What are the standard default hyperparameters for Adam?",
    "options": ["lr=0.1, beta1=0.5, beta2=0.5", "lr=0.001, beta1=0.9, beta2=0.999, epsilon=1e-8", "lr=0.01, beta1=0.99, beta2=0.99", "lr=0.0001, beta1=0.8, beta2=0.9"],
    "correct": 1,
    "explanation": "The original Adam paper (Kingma & Ba, 2014) recommended lr=0.001, beta1=0.9, beta2=0.999, epsilon=1e-8. These defaults work well for most problems.",
    "stage": "post"
  },
  {
    "question": "Which optimizer is the modern default for training transformers and LLMs?",
    "options": ["Vanilla SGD", "SGD with momentum", "RMSProp", "AdamW"],
    "correct": 3,
    "explanation": "AdamW (Adam with decoupled weight decay) is used to train BERT, GPT, LLaMA, and virtually all modern transformers. It combines adaptive learning rates with proper weight decay regularization.",
    "stage": "post"
  }
]