Active Sampling for Min-Max Fairness
- URL: http://arxiv.org/abs/2006.06879v3
- Date: Fri, 17 Jun 2022 13:19:33 GMT
- Title: Active Sampling for Min-Max Fairness
- Authors: Jacob Abernethy, Pranjal Awasthi, Matth\"aus Kleindessner, Jamie
Morgenstern, Chris Russell, Jie Zhang
- Abstract summary: We propose simple active sampling and reweighting strategies for optimizing min-max fairness.
The ease of implementation and the generality of our robust formulation make it an attractive option for improving model performance on disadvantaged groups.
For convex learning problems, such as linear or logistic regression, we provide a fine-grained analysis, proving the rate of convergence to a min-max fair solution.
- Score: 28.420886416425077
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose simple active sampling and reweighting strategies for optimizing
min-max fairness that can be applied to any classification or regression model
learned via loss minimization. The key intuition behind our approach is to use
at each timestep a datapoint from the group that is worst off under the current
model for updating the model. The ease of implementation and the generality of
our robust formulation make it an attractive option for improving model
performance on disadvantaged groups. For convex learning problems, such as
linear or logistic regression, we provide a fine-grained analysis, proving the
rate of convergence to a min-max fair solution.
Related papers
- Feasible Learning [78.6167929413604]
We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample.
Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
arXiv Detail & Related papers (2025-01-24T20:39:38Z) - Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications [79.53938312089308]
The MIDX-Sampler is a novel adaptive sampling strategy based on an inverted multi-index approach.
Our method is backed by rigorous theoretical analysis, addressing key concerns such as sampling bias, gradient bias, convergence rates, and generalization error bounds.
arXiv Detail & Related papers (2025-01-15T04:09:21Z) - Fair and Accurate Regression: Strong Formulations and Algorithms [5.93858665501805]
This paper introduces mixed-integer optimization methods to solve regression problems that incorporate metrics.
We propose an exact formulation for training fair regression models.
Numerical experiments conducted on fair least squares and fair logistic regression problems show competitive statistical performance.
arXiv Detail & Related papers (2024-12-22T18:04:54Z) - Model-Free Active Exploration in Reinforcement Learning [53.786439742572995]
We study the problem of exploration in Reinforcement Learning and present a novel model-free solution.
Our strategy is able to identify efficient policies faster than state-of-the-art exploration approaches.
arXiv Detail & Related papers (2024-06-30T19:00:49Z) - Soft Preference Optimization: Aligning Language Models to Expert Distributions [40.84391304598521]
SPO is a method for aligning generative models, such as Large Language Models (LLMs), with human preferences.
SPO integrates preference loss with a regularization term across the model's entire output distribution.
We showcase SPO's methodology, its theoretical foundation, and its comparative advantages in simplicity, computational efficiency, and alignment precision.
arXiv Detail & Related papers (2024-04-30T19:48:55Z) - Regression-aware Inference with LLMs [52.764328080398805]
We show that an inference strategy can be sub-optimal for common regression and scoring evaluation metrics.
We propose alternate inference strategies that estimate the Bayes-optimal solution for regression and scoring metrics in closed-form from sampled responses.
arXiv Detail & Related papers (2024-03-07T03:24:34Z) - Self-Supervised Dataset Distillation for Transfer Learning [77.4714995131992]
We propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL)
We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is textitbiased due to randomness originating from data augmentations or masking.
We empirically validate the effectiveness of our method on various applications involving transfer learning.
arXiv Detail & Related papers (2023-10-10T10:48:52Z) - Modeling the Second Player in Distributionally Robust Optimization [90.25995710696425]
We argue for the use of neural generative models to characterize the worst-case distribution.
This approach poses a number of implementation and optimization challenges.
We find that the proposed approach yields models that are more robust than comparable baselines.
arXiv Detail & Related papers (2021-03-18T14:26:26Z) - Model-based Policy Optimization with Unsupervised Model Adaptation [37.09948645461043]
We investigate how to bridge the gap between real and simulated data due to inaccurate model estimation for better policy optimization.
We propose a novel model-based reinforcement learning framework AMPO, which introduces unsupervised model adaptation.
Our approach achieves state-of-the-art performance in terms of sample efficiency on a range of continuous control benchmark tasks.
arXiv Detail & Related papers (2020-10-19T14:19:42Z) - Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization
without Compounding Errors [10.906666680425754]
We propose a Dyna-style model-based reinforcement learning algorithm, which we called Maximum Entropy Model Rollouts (MEMR)
To eliminate the compounding errors, we only use our model to generate single-step rollouts.
arXiv Detail & Related papers (2020-06-08T21:38:15Z)
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.