Calibrated Regression Against An Adversary Without Regret

• URL: http://arxiv.org/abs/2302.12196v3
• Date: Tue, 4 Jun 2024 21:33:04 GMT
• Title: Calibrated Regression Against An Adversary Without Regret
• Authors: Shachi Deshpande, Charles Marx, Volodymyr Kuleshov,
• Abstract summary: We introduce online algorithms guaranteed to achieve these goals on arbitrary streams of data points. Specifically, our algorithms produce forecasts that are (1) calibrated -- i.e., an 80% confidence interval contains the true outcome 80% of the time. We implement a post-hoc recalibration strategy that provably achieves these goals in regression.
• Score: 10.470326550507117
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We are interested in probabilistic prediction in online settings in which data does not follow a probability distribution. Our work seeks to achieve two goals: (1) producing valid probabilities that accurately reflect model confidence; and (2) ensuring that traditional notions of performance (e.g., high accuracy) still hold. We introduce online algorithms guaranteed to achieve these goals on arbitrary streams of data points, including data chosen by an adversary. Specifically, our algorithms produce forecasts that are (1) calibrated -- i.e., an 80% confidence interval contains the true outcome 80% of the time -- and (2) have low regret relative to a user-specified baseline model. We implement a post-hoc recalibration strategy that provably achieves these goals in regression; previous algorithms applied to classification or achieved (1) but not (2). In the context of Bayesian optimization, an online model-based decision-making task in which the data distribution shifts over time, our method yields accelerated convergence to improved optima.

Related papers

• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• Calibrated Probabilistic Forecasts for Arbitrary Sequences [58.54729945445505]
  Real-world data streams can change unpredictably due to distribution shifts, feedback loops and adversarial actors. We present a forecasting framework ensuring valid uncertainty estimates regardless of how data evolves.
  arXiv  Detail & Related papers  (2024-09-27T21:46:42Z)
• Reconciling Model Multiplicity for Downstream Decision Making [24.335927243672952]
  We show that even when the two predictive models approximately agree on their individual predictions almost everywhere, it is still possible for their induced best-response actions to differ on a substantial portion of the population. We propose a framework that calibrates the predictive models with regard to both the downstream decision-making problem and the individual probability prediction.
  arXiv  Detail & Related papers  (2024-05-30T03:36:46Z)
• Uncertainty for Active Learning on Graphs [70.44714133412592]
  Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models. We benchmark Uncertainty Sampling beyond predictive uncertainty and highlight a significant performance gap to other Active Learning strategies. We develop ground-truth Bayesian uncertainty estimates in terms of the data generating process and prove their effectiveness in guiding Uncertainty Sampling toward optimal queries.
  arXiv  Detail & Related papers  (2024-05-02T16:50:47Z)
• Calibrated Selective Classification [34.08454890436067]
  We develop a new approach to selective classification in which we propose a method for rejecting examples with "uncertain" uncertainties. We present a framework for learning selectively calibrated models, where a separate selector network is trained to improve the selective calibration error of a given base model. We demonstrate the empirical effectiveness of our approach on multiple image classification and lung cancer risk assessment tasks.
  arXiv  Detail & Related papers  (2022-08-25T13:31:09Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Online Calibrated and Conformal Prediction Improves Bayesian Optimization [10.470326550507117]
  This paper studies which uncertainties are needed in model-based decision-making and in Bayesian optimization. Maintaining calibration, however, can be challenging when the data is non-stationary and depends on our actions. We propose using simple algorithms based on online learning to provably maintain calibration on non-i.i.d. data.
  arXiv  Detail & Related papers  (2021-12-08T23:26:23Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• Privacy Preserving Recalibration under Domain Shift [119.21243107946555]
  We introduce a framework that abstracts out the properties of recalibration problems under differential privacy constraints. We also design a novel recalibration algorithm, accuracy temperature scaling, that outperforms prior work on private datasets.
  arXiv  Detail & Related papers  (2020-08-21T18:43:37Z)

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.