Calibration of heterogeneous treatment effects in randomized experiments
Machine learning is commonly used to estimate the heterogeneous treatment effects (HTEs)
in randomized experiments. Using large-scale randomized experiments on the Facebook …
in randomized experiments. Using large-scale randomized experiments on the Facebook …
Streamai: Dealing with challenges of continual learning systems for serving ai in production
M Barry, A Bifet, JL Billy - 2023 IEEE/ACM 45th International …, 2023 - ieeexplore.ieee.org
How to build, deploy, update & maintain dynamic models which continuously learn from
streaming data? This paper covers the industrialization aspects of these questions in …
streaming data? This paper covers the industrialization aspects of these questions in …
StreamMLOps: Operationalizing Online Learning for Big Data Streaming & Real-Time Applications
Continuously learning and serving from evolving streaming data and serving in real-time is a
challenging problem. Traditionally, data is partitioned and processed in batches to train …
challenging problem. Traditionally, data is partitioned and processed in batches to train …
[PDF][PDF] Streammlops: Online learning in practice from big data streams & real-time applications
Continuously Learning and serving from evolving streaming data to real-time inference in
production is a challenging problem. Traditionally, data is partitioned and processed in …
production is a challenging problem. Traditionally, data is partitioned and processed in …
Smartchoices: Augmenting software with learned implementations
We are living in a golden age of machine learning. Powerful models perform many tasks far
better than is possible using traditional software engineering approaches alone. However …
better than is possible using traditional software engineering approaches alone. However …
Calibration of heterogeneous treatment effects in random experiments
Abstract Machine learning is commonly used to estimate the heterogeneous treatment
effects (HTEs) in randomized experiments. Using a large-scale randomized experiment on …
effects (HTEs) in randomized experiments. Using a large-scale randomized experiment on …
Experimentation, deployment and monitoring Machine Learning models: Approaches for applying MLOps
D Nogare, IF Silveira - arXiv preprint arXiv:2408.11112, 2024 - arxiv.org
In recent years, Data Science has become increasingly relevant as a support tool for
industry, significantly enhancing decision-making in a way never seen before. In this context …
industry, significantly enhancing decision-making in a way never seen before. In this context …
On a Scale-Invariant Approach to Bundle Recommendations in Candy Crush Saga
S Katsarou, F Carminati, M Dlask, M Braojos… - arXiv preprint arXiv …, 2024 - arxiv.org
A good understanding of player preferences is crucial for increasing content relevancy,
especially in mobile games. This paper illustrates the use of attentive models for producing …
especially in mobile games. This paper illustrates the use of attentive models for producing …
Efficient Multi-stage Inference on Tabular Data
DS Johnson, IL Markov - arXiv preprint arXiv:2303.11580, 2023 - arxiv.org
Many ML applications and products train on medium amounts of input data but get
bottlenecked in real-time inference. When implementing ML systems, conventional wisdom …
bottlenecked in real-time inference. When implementing ML systems, conventional wisdom …
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 …
engineering effort. Upon sufficiently broad adoption, such platforms reach economies of …