- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper tries to solve the high computation cost problem of bayesian inference of DEQs. The paper propose a sequential inference method by combining similar successive parameter samples to reduce computation cost. Experiments have shown up to 3x speedup while maintaining comparable predictive accuracy.
Critical strengths
- This paper studies a practical computation bottleneck problem of uncertainty estimation for DEQs.
- The paper proposed method appears intuitively simple and effective as a quick add on to existing bayesian methods.
Critical weaknesses
- The novelty is limited. The proposed method appears incremental that directly builds on existing bayesian approximations and simply use sampling and warm starts to speed up, with no theoretical guarantee.
- Limited empirical evidence. The experiment only evaluate on SWAG and SGLD, I wonder if their method would expand to more methods. Furthermore, the task are generally toy regression problems that are too simple. This limited coverage is insufficient evidence for claimed generality and scalability.
Questions for authors
Please try to address my weakness.
Please engage in the discussion
Authors: you have not responded to any review. Please reply to the comments and engage in the discussion.