No Free Delivery Service: Epistemic limits of passive data collection in complex social systems

• URL: http://arxiv.org/abs/2411.13653v1
• Date: Wed, 20 Nov 2024 19:01:03 GMT
• Title: No Free Delivery Service: Epistemic limits of passive data collection in complex social systems
• Authors: Maximilian Nickel,
• Abstract summary: I will show that for widely considered inference settings in complex social systems the train-test paradigm does not only lack a justification but is indeed invalid for any risk estimator. I am illustrating these results via the widely used MovieLens benchmark and conclude by discussing the implications of these results for AI in social systems.
• Score: 11.990018360916553
• License:
• Abstract: Rapid model validation via the train-test paradigm has been a key driver for the breathtaking progress in machine learning and AI. However, modern AI systems often depend on a combination of tasks and data collection practices that violate all assumptions ensuring test validity. Yet, without rigorous model validation we cannot ensure the intended outcomes of deployed AI systems, including positive social impact, nor continue to advance AI research in a scientifically sound way. In this paper, I will show that for widely considered inference settings in complex social systems the train-test paradigm does not only lack a justification but is indeed invalid for any risk estimator, including counterfactual and causal estimators, with high probability. These formal impossibility results highlight a fundamental epistemic issue, i.e., that for key tasks in modern AI we cannot know whether models are valid under current data collection practices. Importantly, this includes variants of both recommender systems and reasoning via large language models, and neither na\"ive scaling nor limited benchmarks are suited to address this issue. I am illustrating these results via the widely used MovieLens benchmark and conclude by discussing the implications of these results for AI in social systems, including possible remedies such as participatory data curation and open science.

Related papers

• Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them) [14.396431159723297]
  We show that conformal prediction can theoretically be extended to textitany joint data distribution. Although the most general case is exceedingly impractical to compute, for concrete practical applications we outline a procedure for deriving specific conformal algorithms.
  arXiv  Detail & Related papers  (2024-05-10T17:40:24Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• From Static Benchmarks to Adaptive Testing: Psychometrics in AI Evaluation [60.14902811624433]
  We discuss a paradigm shift from static evaluation methods to adaptive testing. This involves estimating the characteristics and value of each test item in the benchmark and dynamically adjusting items in real-time. We analyze the current approaches, advantages, and underlying reasons for adopting psychometrics in AI evaluation.
  arXiv  Detail & Related papers  (2023-06-18T09:54:33Z)
• Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction [50.79827516897913]
  We introduce an interpretable paradigm for trajectory prediction that distributes the uncertainty among semantic concepts. We validate our approach on real-world autonomous driving data, demonstrating superior performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-11-16T06:28:20Z)
• Explanation-by-Example Based on Item Response Theory [0.0]
  This research explores the Item Response Theory (IRT) as a tool to explaining the models and measuring the level of reliability of the Explanation-by-Example approach. From the test set, 83.8% of the errors are from instances in which the IRT points out the model as unreliable.
  arXiv  Detail & Related papers  (2022-10-04T14:36:33Z)
• Discovering and Validating AI Errors With Crowdsourced Failure Reports [10.4818618376202]
  We introduce crowdsourced failure reports, end-user descriptions of how or why a model failed, and show how developers can use them to detect AI errors. We also design and implement Deblinder, a visual analytics system for synthesizing failure reports. In semi-structured interviews and think-aloud studies with 10 AI practitioners, we explore the affordances of the Deblinder system and the applicability of failure reports in real-world settings.
  arXiv  Detail & Related papers  (2021-09-23T23:26:59Z)
• DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation [57.358212277226315]
  In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms. This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk. We propose a more data-efficient IfO algorithm
  arXiv  Detail & Related papers  (2021-03-31T23:46:32Z)
• Offline Learning for Planning: A Summary [0.0]
  Training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Data sets containing recorded experiences of intelligent agents performing various tasks are accessible on the internet. In this paper we adumbrate the ideas motivating the development of the state-of-the-art offline learning baselines.
  arXiv  Detail & Related papers  (2020-10-05T11:41:11Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)
• Measuring the Complexity of Domains Used to Evaluate AI Systems [0.48951183832371004]
  We propose a theory for measuring the complexity between varied domains. An application of this measure is then demonstrated to show its effectiveness as a tool in varied situations. We propose the future use of such a complexity metric for use in computing an AI system's intelligence.
  arXiv  Detail & Related papers  (2020-09-18T21:53:07Z)
• An Uncertainty-based Human-in-the-loop System for Industrial Tool Wear Analysis [68.8204255655161]
  We show that uncertainty measures based on Monte-Carlo dropout in the context of a human-in-the-loop system increase the system's transparency and performance. A simulation study demonstrates that the uncertainty-based human-in-the-loop system increases performance for different levels of human involvement.
  arXiv  Detail & Related papers  (2020-07-14T15:47:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.