- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper considered the problem of learning from multiple experts. In the standard setting, based on observed features, the router can either use its own prediction, or alternatively, route these features to one of a set of possible experts, and use that prediction. The goal of the router is therefore to learn the best routing function to an expert (based on the observed features), in an online manner. In this paper, this standard setting is extended with the possibility of not accepting the expert decision as is, but rather correct it before making the final prediction, with a learnable correction function. Most of the paper is devoted to a description of the various components of this setting, and how each one of them is specifically performed, and also how the performance is measured. Theorem 6.3 is the main theoretical contribution, showing a universal regret of . A few experiments show improvement in the prediction error.
Critical strengths
- The considered regret is a strong conditional version, in which the reference correction function is allowed to depend on the history.
Critical weaknesses
-
The model is fairly complicated, and includes many “ad-hoc” assumptions on specific aspects – the specific structure of the correction based on residual, the polynomial correction function (rather than a general class), the shared representation setup, the pooling mechanism. Later on features given by and so on. A “cleaner”, simpler, version of this setting would allow to highlight how the ability to correct an expert affects the regret (beyond behavior).
-
As a result, the organization is poor and difficult to follow. The setting, the algorithm solution, and the theoretical guarantees are all mixed throughout the paper, with the setting being partially described, then some algorithmic aspects such as response fit and pooling, then theoretical guarantee (Lemma 5.1), then back to more assumption on the setting, algorithmic aspect in (15) (with parameters that appear out of the blue), along with early references to Section 6 (Theory). The paragraphs after (15) in Section 5.3. e.g. are difficult to read since they use many unexplained terms and refer to later equations and assumptions.
-
While the regret bound is on the order , it is not instance-dependent, and so it does not indicate how the complexity of the instance affects the difficulty of learning. This does not allow to capture which instances the correction of the expert is beneficial/non-beneficial but difficult/easy to learn.
Questions for authors
-
Section “5.1 learning the response - response fits” is unclear. What is the role of the vectors and ? Why does it make sense to assume that they are different at each round, and that they are available at each round? In (10) why is the projected shared proposal is denoted “population” when it is also an empirical quantity?
-
Section “5.1 learning the response - pooling”: Why is exponential weighting reasonable for a regression problem? It seems that a convex mixture of coefficients can be beneficial. Can you justify it here?
-
Comment: Lemma 5.1 seems out of place. It is based on future assumption and equations, and also seems technical.
-
Comment: To add to the confusion, the Response-aware-UCB algorithm is never explicitly mentioned. It is probably described at the end of page 6, but this is just an (educated) guess.
-
Clarification: What is “an unfinished response” (line 370)?
Thank you for clarifying the theory and the experiments. Based on the paper and the authors' response, the submission makes a meaningful theoretical contribution. However, its theoretical advantage over the calibrated unit-weight router holds only in certain parameter regimes. The new experiments help explain when the sample weights affect routing decisions, but the gains over the unweighted UCB baseline using the same correction learner remain small. Also, although the calibration is key to the theoretical guarantee, it is still unclear how to obtain the required constants on the benchmarks. Thus, it remains unclear how to apply the theorem’s calibration to these benchmarks and how much it would help.