• Corpus ID: 231861405

Patterns, predictions, and actions: A story about machine learning

@article{Hardt2021PatternsPA,
  title={Patterns, predictions, and actions: A story about machine learning},
  author={Moritz Hardt and Benjamin Recht},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.05242}
}
This graduate textbook on machine learning tells a story of how patterns in data support predictions and consequential actions. Starting with the foundations of decision making, we cover representation, optimization, and generalization as the constituents of supervised learning. A chapter on datasets as benchmarks examines their histories and scientific bases. Self-contained introductions to causality, the practice of causal inference, sequential decision making, and reinforcement learning… 
Machine learning in the social and health sciences
TLDR
A meta-mapping of research questions in the social and health sciences to appropriate ML approaches is provided, by incorporating the necessary requirements to statistical analysis in these disciplines, and may help to advance the uptake of ML in social andhealth sciences while also pointing to possible limitations and ways of addressing them.
Are We Learning Yet? A Meta Review of Evaluation Failures Across Machine Learning
  • Thomas Liao
  • Computer Science
    NeurIPS Datasets and Benchmarks
  • 2021
TLDR
A meta-review of 107 survey papers from computer vision, natural language processing, recommender systems, reinforcement learning, graph processing, metric learning, and more is conducted, organizing a wide range of surprisingly consistent critique into a concrete taxonomy of observed failure modes.
Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
TLDR
This paper shows how bringing recent results on equivariant representation learning (for studying symmetries in neural networks) in-stantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution.
Probabilistic design of optimal sequential decision-making algorithms in learning and control
TLDR
This survey is focused on certain sequential decision-making problems that involve optimizing over probability functions and revisits popular learning and control algorithms, showing that these naturally arise from suitable variations on the formulation mixed with different resolution methods.
Prospective Learning: Back to the Future
TLDR
It is argued that a paradigm shift from retrospective to prospective learning will enable the communities that study intelligence to unite and overcome existing bottlenecks to more effectively explain, augment, and engineer intelligences.
Communication-Efficient and Byzantine-Robust Distributed Learning With Error Feedback
TLDR
A communication-efficient distributed learning algorithm that is robust against Byzantine worker machines, and a distributed gradient-descent algorithm that performs a simple thresholding based on gradient norms to mitigate Byzantine failures.
Machine Learning for Health: Algorithm Auditing & Quality Control
TLDR
This editorial gives a summary of ongoing work towards an integrated framework of algorithm auditing and quality control that provides a path towards the effective and reliable application of ML systems in healthcare.
Retiring Adult: New Datasets for Fair Machine Learning
TLDR
A suite of new datasets derived from US Census surveys that extend the existing data ecosystem for research on fair machine learning and create prediction tasks relating to income, employment, health, transportation, and housing are created.
Fundamental Limits of Controlled Stochastic Dynamical Systems: An Information-Theoretic Approach
TLDR
Generic Lp bounds that hold for any causal (stabilizing) controllers and any stochastic disturbances, by an information-theoretic analysis are derived.