Seems like these guys just wasted $11k to erroneously claim, “deep learning bad! Simple is better!”
There’s definitely use for these classical, model-based methods, for sure. But a contrived comparison claiming they’re king is just misinformation.
Eg, here are a number of issues with classical techniques where dl succeeds (‘they’ here refers to classical techniques):
- they often don’t support missing/corrupt data
- they focus on linear relationships and not complex joint distributions
- they focus on fixed temporal dependence that must be diagnosed and specified a priori
- they take as input univariate, not multiple interval, data
- they focus on one-step forecasts, not long time horizons
- they’re highly parameterized and rigid to assumptions
- they fail for cold start problems
A more nuanced comparison would do well to mention these.
There’s definitely use for these classical, model-based methods, for sure. But a contrived comparison claiming they’re king is just misinformation.
Eg, here are a number of issues with classical techniques where dl succeeds (‘they’ here refers to classical techniques):
- they often don’t support missing/corrupt data
- they focus on linear relationships and not complex joint distributions
- they focus on fixed temporal dependence that must be diagnosed and specified a priori
- they take as input univariate, not multiple interval, data
- they focus on one-step forecasts, not long time horizons
- they’re highly parameterized and rigid to assumptions
- they fail for cold start problems
A more nuanced comparison would do well to mention these.