1. |
- Souza, Artur, et al.
(författare)
-
Bayesian Optimization with a Prior for the Optimum
- 2021
-
Ingår i: Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2021, Proceedings. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. - 9783030865221 ; 12977 LNAI, s. 265-296
-
Konferensbidrag (refereegranskat)abstract
- While Bayesian Optimization (BO) is a very popular method for optimizing expensive black-box functions, it fails to leverage the experience of domain experts. This causes BO to waste function evaluations on bad design choices (e.g., machine learning hyperparameters) that the expert already knows to work poorly. To address this issue, we introduce Bayesian Optimization with a Prior for the Optimum (BOPrO). BOPrO allows users to inject their knowledge into the optimization process in the form of priors about which parts of the input space will yield the best performance, rather than BO’s standard priors over functions, which are much less intuitive for users. BOPrO then combines these priors with BO’s standard probabilistic model to form a pseudo-posterior used to select which points to evaluate next. We show that BOPrO is around 6.67 × faster than state-of-the-art methods on a common suite of benchmarks, and achieves a new state-of-the-art performance on a real-world hardware design application. We also show that BOPrO converges faster even if the priors for the optimum are not entirely accurate and that it robustly recovers from misleading priors.
|
|
2. |
- Swamy, Tushar, et al.
(författare)
-
Homunculus : Auto-Generating Efficient Data-Plane ML Pipelines for Datacenter Networks
- 2023
-
Ingår i: ASPLOS 2023 - Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems. - New York, NY, USA : ACM. - 9781450399180 ; 3, s. 329-342
-
Konferensbidrag (refereegranskat)abstract
- Support for Machine Learning (ML) applications in networking has significantly improved over the last decade. The availability of public datasets and programmable switching fabrics (including low-level languages to program them) presents a full-stack to the programmer for deploying in-network ML. However, the diversity of tools involved, coupled with complex optimization tasks of ML model design and hyperparameter tuning while complying with the network constraints (like throughput and latency), puts the onus on the network operator to be an expert in ML, network design, and programmable hardware. We present Homunculus, a high-level framework that enables network operators to specify their ML requirements in a declarative rather than imperative way. Homunculus takes as input the training data and accompanying network and hardware constraints, and automatically generates and installs a suitable model onto the underlying switching target. It performs model design-space exploration, training, and platform code-generation as compiler stages, leaving network operators to focus on acquiring high-quality network data. Our evaluations on real-world ML applications show that Homunculus's generated models achieve up to 12% better F1 scores compared to hand-tuned alternatives, while operating within the resource limits of the underlying targets. We further demonstrate the high performance and increased reactivity (seconds to nanoseconds) of the generated models on emerging per-packet ML platforms to showcase Homunculus's timely and practical significance.
|
|