The False Dawn: Reevaluating Google's Reinforcement Learning for Chip Macro Placement

Reinforcement learning (RL) for physical design of silicon chips in a Google 2021 Nature paper stirred controversy due to poorly documented claims that raised eyebrows and attracted critical media coverage. The Nature paper withheld most inputs needed to produce reported results and some critical steps in the methodology. But two separate evaluations filled in the gaps and demonstrated that Google RL lags behind human designers, behind a well-known algorithm (Simulated Annealing), and also behind generally-available commercial software. Crosschecked data indicate that the integrity of the Nature paper is substantially undermined owing to errors in the conduct, analysis and reporting.

Scalable End-to-End ML Platforms: from AutoML to Self-serve

ML platforms help enable intelligent data-driven applications and maintain them with limited engineering effort. Upon sufficiently broad adoption, such platforms reach economies of scale that bring greater component reuse while improving efficiency of system development and maintenance. For an end-to-end ML platform with broad adoption, scaling relies on pervasive ML automation and system integration to reach the quality we term self-serve that we define with ten requirements and six optional capabilities. With this in mind, we identify long-term goals for platform development, discuss related tradeoffs and future work. Our reasoning is illustrated on two commercially-deployed end-to-end ML platforms that host hundreds of real-time use cases -- one general-purpose and one specialized.

Practical Knowledge Distillation: Using DNNs to Beat DNNs

For tabular data sets, we explore data and model distillation, as well as data denoising. These techniques improve both gradient-boosting models and a specialized DNN architecture. While gradient boosting is known to outperform DNNs on tabular data, we close the gap for datasets with 100K+ rows and give DNNs an advantage on small data sets. We extend these results with input-data distillation and optimized ensembling to help DNN performance match or exceed that of gradient boosting. As a theoretical justification of our practical method, we prove its equivalence to classical cross-entropy knowledge distillation. We also qualitatively explain the superiority of DNN ensembles over XGBoost on small data sets. For an industry end-to-end real-time ML platform with 4M production inferences per second, we develop a model-training workflow based on data sampling that distills ensembles of models into a single gradient-boosting model favored for high-performance real-time inference, without performance loss. Empirical evaluation shows that the proposed combination of methods consistently improves model accuracy over prior best models across several production applications deployed worldwide.

Looper: An end-to-end ML platform for product decisions

Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users and systems, e.g., compute infrastructure. For broader adoption, this practice must (i) accommodate software engineers without ML backgrounds, and (ii) provide mechanisms to optimize for product goals. In this work, we describe general principles and a specific end-to-end ML platform, Looper, which offers easy-to-use APIs for decision-making and feedback collection. Looper supports the full end-to-end ML lifecycle from online data collection to model training, deployment, inference, and extends support to evaluation and tuning against product goals. We outline the platform architecture and overall impact of production deployment -- Looper currently hosts 700 ML models and makes 6 million decisions per second. We also describe the learning curve and summarize experiences of platform adopters.