Approximate Regions of Attraction in Learning with Decision-Dependent Distributions

• URL: http://arxiv.org/abs/2107.00055v4
• Date: Mon, 24 Apr 2023 20:36:10 GMT
• Title: Approximate Regions of Attraction in Learning with Decision-Dependent Distributions
• Authors: Roy Dong and Heling Zhang and Lillian J. Ratliff
• Abstract summary: We analyze repeated risk minimization as the trajectories of the gradient flows of performative risk minimization. We provide conditions to characterize the region of attraction for the various equilibria in this setting. We introduce the notion of performative alignment, which provides a geometric condition on the convergence of repeated risk minimization to performative risk minimizers.
• Score: 11.304363655760513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As data-driven methods are deployed in real-world settings, the processes that generate the observed data will often react to the decisions of the learner. For example, a data source may have some incentive for the algorithm to provide a particular label (e.g. approve a bank loan), and manipulate their features accordingly. Work in strategic classification and decision-dependent distributions seeks to characterize the closed-loop behavior of deploying learning algorithms by explicitly considering the effect of the classifier on the underlying data distribution. More recently, works in performative prediction seek to classify the closed-loop behavior by considering general properties of the mapping from classifier to data distribution, rather than an explicit form. Building on this notion, we analyze repeated risk minimization as the perturbed trajectories of the gradient flows of performative risk minimization. We consider the case where there may be multiple local minimizers of performative risk, motivated by situations where the initial conditions may have significant impact on the long-term behavior of the system. We provide sufficient conditions to characterize the region of attraction for the various equilibria in this settings. Additionally, we introduce the notion of performative alignment, which provides a geometric condition on the convergence of repeated risk minimization to performative risk minimizers.

Related papers

• Optimal Classification under Performative Distribution Shift [13.508249764979075]
  We propose a novel view in which performative effects are modelled as push-forward measures. We prove the convexity of the performative risk under a new set of assumptions. We also establish a connection with adversarially robust classification by reformulating the minimization of the performative risk as a min-max variational problem.
  arXiv  Detail & Related papers  (2024-11-04T12:20:13Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance. Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction [55.77015419028725]
  We develop methods that permit valid control of risk when threshold and tradeoff parameters are chosen adaptively. Our methodology supports monotone and nearly-monotone risks, but otherwise makes no distributional assumptions.
  arXiv  Detail & Related papers  (2024-03-28T17:28:06Z)
• Distributional Method for Risk Averse Reinforcement Learning [0.0]
  We introduce a distributional method for learning the optimal policy in risk averse Markov decision process. We assume sequential observations of states, actions, and costs and assess the performance of a policy using dynamic risk measures.
  arXiv  Detail & Related papers  (2023-02-27T19:48:42Z)
• STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning [111.75423966239092]
  We propose an exploration incentive in terms of the integral probability metric (IPM) between a current estimate of the transition model and the unknown optimal. Based on KSD, we develop a novel algorithm algo: textbfSTEin information dirtextbfEcted exploration for model-based textbfReinforcement LearntextbfING.
  arXiv  Detail & Related papers  (2023-01-28T00:49:28Z)
• Optimizing the Performative Risk under Weak Convexity Assumptions [0.0]
  In performative prediction, a predictive model impacts the distribution that generates future data. Prior work has identified a pair of general conditions on the loss and the mapping from model parameters to distributions that implies convexity the performative risk. In this paper, we relax these assumptions, without sacrificing the amenability of the performative minimization risk problem for iterative optimization methods.
  arXiv  Detail & Related papers  (2022-09-02T01:07:09Z)
• Mitigating sampling bias in risk-based active learning via an EM algorithm [0.0]
  Risk-based active learning is an approach to developing statistical classifiers for online decision-support. Data-label querying is guided according to the expected value of perfect information for incipient data points. Semi-supervised approach counteracts sampling bias by incorporating pseudo-labels for unlabelled data via an EM algorithm.
  arXiv  Detail & Related papers  (2022-06-25T08:48:25Z)
• Self-Certifying Classification by Linearized Deep Assignment [65.0100925582087]
  We propose a novel class of deep predictors for classifying metric data on graphs within PAC-Bayes risk certification paradigm. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables learning posterior distributions on the hypothesis space.
  arXiv  Detail & Related papers  (2022-01-26T19:59:14Z)
• Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization [77.8735802150511]
  We propose a cross-sample adversarial debiasing (CSAD) method to remove the bias information misused by the target task. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-08-11T21:17:02Z)
• Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning [57.88785630755165]
  Empirical risk minimization (ERM) is the workhorse of machine learning, but its model-agnostic guarantees can fail when we use adaptively collected data. We study a generic importance sampling weighted ERM algorithm for using adaptively collected data to minimize the average of a loss function over a hypothesis class. For policy learning, we provide rate-optimal regret guarantees that close an open gap in the existing literature whenever exploration decays to zero.
  arXiv  Detail & Related papers  (2021-06-03T09:50:13Z)
• Principled learning method for Wasserstein distributionally robust optimization with local perturbations [21.611525306059985]
  Wasserstein distributionally robust optimization (WDRO) attempts to learn a model that minimizes the local worst-case risk in the vicinity of the empirical data distribution. We propose a minimizer based on a novel approximation theorem and provide the corresponding risk consistency results. Our results show that the proposed method achieves significantly higher accuracy than baseline models on noisy datasets.
  arXiv  Detail & Related papers  (2020-06-05T09:32:37Z)

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.