Questions tagged [variance]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
1answer
21 views

How does high entropy targets relate to less variance of the gradient between training cases?

I've been trying to understand the Distilling the Knowledge in a Neural Network paper by Hinton et al. But I cannot fully understand this: When the soft targets have high entropy, they provide much ...
0
votes
0answers
25 views

Which off-policy policy gradient estimator has lower variance?

Let $\pi_\theta$ be a target policy and $\beta_\theta$ be a behavior policy. I have seen the following 2 policy gradient estimators in the literature: $$ \operatorname*{E}_{\tau \sim \beta_\theta} \...
1
vote
1answer
589 views

Is there a bias-variance equivalent in unsupervised learning?

In supervised learning, bias, variance are pretty easy to calculate with labeled data. I was wondering if there's something equivalent in unsupervised learning, or like a way to estimate such things? ...
3
votes
0answers
76 views

Why does this formula $\sigma^2 + \frac{1}{T}\sum_{t=1}^Tf^{\hat{W_t}}(x)^Tf^{\hat{W_t}}(x_t)-E(y)^TE(y)$ approximate the variance?

How does: $$\text{Var}(y) \approx \sigma^2 + \frac{1}{T}\sum_{t=1}^Tf^{\hat{W_t}}(x)^Tf^{\hat{W_t}}(x_t)-E(y)^TE(y)$$ approximate variance? I'm currently reading What Uncertainties Do We Need in ...