[vighneshiyer]

Existing mixed-placement algorithms depend on hyperparameters, heuristics, and initial states / randomness. If afforded more compute resources, they can explore a much wider space and in theory come up with better solutions. Some algorithms like simulated annealing are easy to modify to exploit arbitrarily more compute resources. Indeed, I believe the comparison of AlphaChip to alternatives would be fairer if compute resources and allowed runtime were matched.

In fact, existing algorithms such as naive simulated annealing can be easily augmented with ML (e.g. using state embeddings to optimize hyperparameters for a given problem instance, or using a regression model to fine-tune proxy costs to better correlate with final QoR). Indeed, I strongly suspect commercial CAD software is already applying ML in many ways for mixed-placement and other CAD algorithms. The criticism against AlphaChip isn't about rejecting any application of ML to EDA CAD algorithms, but rather the particular formulation they used and objections to their reported results / comparisons.

[sdenton4]

That sounds like future work for simulated annealing fans to engage in, quite honestly, rather than something that needs to be addressed immediately in a paper proposing an alternative method. The proposed method accomplished what it set out to do, surpassing current methods; others are free to explore different hyperparameters to surpass the quality again... This is, ultimately, why we build benchmark tasks: if you want to prove you know how to do it better, one is free to just go do it better instead of whining about what the competition did or didn't try on one's behalf.