Alternative Microfoundations for Strategic Classification
- URL: http://arxiv.org/abs/2106.12705v1
- Date: Thu, 24 Jun 2021 00:30:58 GMT
- Title: Alternative Microfoundations for Strategic Classification
- Authors: Meena Jagadeesan, Celestine Mendler-D\"unner, Moritz Hardt
- Abstract summary: We show that rational agents with perfect information produce discontinuities in the aggregate response to a decision rule.
optimal decision rules under standard microfoundations maximize a measure of negative externality known as social burden.
Our model retains analytical tractability, leads to more robust insights about stable points, and imposes a lower social burden at optimality.
- Score: 33.67797984699066
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: When reasoning about strategic behavior in a machine learning context it is
tempting to combine standard microfoundations of rational agents with the
statistical decision theory underlying classification. In this work, we argue
that a direct combination of these standard ingredients leads to brittle
solution concepts of limited descriptive and prescriptive value. First, we show
that rational agents with perfect information produce discontinuities in the
aggregate response to a decision rule that we often do not observe empirically.
Second, when any positive fraction of agents is not perfectly strategic,
desirable stable points -- where the classifier is optimal for the data it
entails -- cease to exist. Third, optimal decision rules under standard
microfoundations maximize a measure of negative externality known as social
burden within a broad class of possible assumptions about agent behavior.
Recognizing these limitations we explore alternatives to standard
microfoundations for binary classification. We start by describing a set of
desiderata that help navigate the space of possible assumptions about how
agents respond to a decision rule. In particular, we analyze a natural
constraint on feature manipulations, and discuss properties that are sufficient
to guarantee the robust existence of stable points. Building on these insights,
we then propose the noisy response model. Inspired by smoothed analysis and
empirical observations, noisy response incorporates imperfection in the agent
responses, which we show mitigates the limitations of standard
microfoundations. Our model retains analytical tractability, leads to more
robust insights about stable points, and imposes a lower social burden at
optimality.
Related papers
- Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.
We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.
We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
arXiv Detail & Related papers (2024-09-26T21:00:45Z) - Non-linear Welfare-Aware Strategic Learning [10.448052192725168]
This paper studies algorithmic decision-making in the presence of strategic individual behaviors.
We first generalize the agent best response model in previous works to the non-linear setting.
We show the three welfare can attain the optimum simultaneously only under restrictive conditions.
arXiv Detail & Related papers (2024-05-03T01:50:03Z) - Bi-Level Offline Policy Optimization with Limited Exploration [1.8130068086063336]
We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset.
We propose a bi-level structured policy optimization algorithm that models a hierarchical interaction between the policy (upper-level) and the value function (lower-level)
We evaluate our model using a blend of synthetic, benchmark, and real-world datasets for offline RL, showing that it performs competitively with state-of-the-art methods.
arXiv Detail & Related papers (2023-10-10T02:45:50Z) - When Demonstrations Meet Generative World Models: A Maximum Likelihood
Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent.
Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
arXiv Detail & Related papers (2023-02-15T04:14:20Z) - Distributionally Robust Model-Based Offline Reinforcement Learning with
Near-Optimal Sample Complexity [39.886149789339335]
offline reinforcement learning aims to learn to perform decision making from history data without active exploration.
Due to uncertainties and variabilities of the environment, it is critical to learn a robust policy that performs well even when the deployed environment deviates from the nominal one used to collect the history dataset.
We consider a distributionally robust formulation of offline RL, focusing on robust Markov decision processes with an uncertainty set specified by the Kullback-Leibler divergence in both finite-horizon and infinite-horizon settings.
arXiv Detail & Related papers (2022-08-11T11:55:31Z) - Off-Policy Evaluation with Policy-Dependent Optimization Response [90.28758112893054]
We develop a new framework for off-policy evaluation with a textitpolicy-dependent linear optimization response.
We construct unbiased estimators for the policy-dependent estimand by a perturbation method.
We provide a general algorithm for optimizing causal interventions.
arXiv Detail & Related papers (2022-02-25T20:25:37Z) - On the estimation of discrete choice models to capture irrational
customer behaviors [4.683806391173103]
We show how to use partially-ranked preferences to efficiently model rational and irrational customer types from transaction data.
An extensive set of experiments assesses the predictive accuracy of the proposed approach.
arXiv Detail & Related papers (2021-09-08T19:19:51Z) - Minimax Off-Policy Evaluation for Multi-Armed Bandits [58.7013651350436]
We study the problem of off-policy evaluation in the multi-armed bandit model with bounded rewards.
We develop minimax rate-optimal procedures under three settings.
arXiv Detail & Related papers (2021-01-19T18:55:29Z) - Learning Strategies in Decentralized Matching Markets under Uncertain
Preferences [91.3755431537592]
We study the problem of decision-making in the setting of a scarcity of shared resources when the preferences of agents are unknown a priori.
Our approach is based on the representation of preferences in a reproducing kernel Hilbert space.
We derive optimal strategies that maximize agents' expected payoffs.
arXiv Detail & Related papers (2020-10-29T03:08:22Z) - Beyond Individualized Recourse: Interpretable and Interactive Summaries
of Actionable Recourses [14.626432428431594]
We propose a novel model framework called Actionable Recourse agnostic (AReS) to construct global counterfactual explanations.
We formulate a novel objective which simultaneously optimize for correctness of the recourses and interpretability of the explanations.
Our framework can provide decision makers with a comprehensive overview of recourses corresponding to any black box model.
arXiv Detail & Related papers (2020-09-15T15:14:08Z) - Evaluations and Methods for Explanation through Robustness Analysis [117.7235152610957]
We establish a novel set of evaluation criteria for such feature based explanations by analysis.
We obtain new explanations that are loosely necessary and sufficient for a prediction.
We extend the explanation to extract the set of features that would move the current prediction to a target class.
arXiv Detail & Related papers (2020-05-31T05:52:05Z)
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.