Taking a Moment for Distributional Robustness

• URL: http://arxiv.org/abs/2405.05461v1
• Date: Wed, 8 May 2024 23:37:25 GMT
• Title: Taking a Moment for Distributional Robustness
• Authors: Jabari Hastings, Christopher Jung, Charlotte Peale, Vasilis Syrgkanis,
• Abstract summary: We introduce a new min-max objective based on what is known as an adversarial violation violation. We show that in the case of square loss, minimizing the worst-case regret is also equivalent to minimizing the worst-case $ell$-distance to the true conditional expectation.
• Score: 19.49177818405511
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A rich line of recent work has studied distributionally robust learning approaches that seek to learn a hypothesis that performs well, in the worst-case, on many different distributions over a population. We argue that although the most common approaches seek to minimize the worst-case loss over distributions, a more reasonable goal is to minimize the worst-case distance to the true conditional expectation of labels given each covariate. Focusing on the minmax loss objective can dramatically fail to output a solution minimizing the distance to the true conditional expectation when certain distributions contain high levels of label noise. We introduce a new min-max objective based on what is known as the adversarial moment violation and show that minimizing this objective is equivalent to minimizing the worst-case $\ell_2$-distance to the true conditional expectation if we take the adversary's strategy space to be sufficiently rich. Previous work has suggested minimizing the maximum regret over the worst-case distribution as a way to circumvent issues arising from differential noise levels. We show that in the case of square loss, minimizing the worst-case regret is also equivalent to minimizing the worst-case $\ell_2$-distance to the true conditional expectation. Although their objective and our objective both minimize the worst-case distance to the true conditional expectation, we show that our approach provides large empirical savings in computational cost in terms of the number of groups, while providing the same noise-oblivious worst-distribution guarantee as the minimax regret approach, thus making positive progress on an open question posed by Agarwal and Zhang (2022).

Related papers

• Best Arm Identification with Minimal Regret [55.831935724659175]
  Best arm identification problem elegantly amalgamates regret minimization and BAI. Agent's goal is to identify the best arm with a prescribed confidence level. Double KL-UCB algorithm achieves optimality as the confidence level tends to zero.
  arXiv  Detail & Related papers  (2024-09-27T16:46:02Z)
• Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond $1+\alpha$ Moments [10.889739958035536]
  We introduce a new definitional framework to analyze the fine-grained optimality of algorithms. We show that median-of-means is neighborhood optimal, up to constant factors. It is open to find a neighborhood-separated estimator without constant factor slackness.
  arXiv  Detail & Related papers  (2023-11-21T18:50:38Z)
• On the Variance, Admissibility, and Stability of Empirical Risk Minimization [80.26309576810844]
  Empirical Risk Minimization (ERM) with squared loss may attain minimax suboptimal error rates. We show that under mild assumptions, the suboptimality of ERM must be due to large bias rather than variance. We also show that our estimates imply stability of ERM, complementing the main result of Caponnetto and Rakhlin (2006) for non-Donsker classes.
  arXiv  Detail & Related papers  (2023-05-29T15:25:48Z)
• A Dimensionality Reduction Method for Finding Least Favorable Priors with a Focus on Bregman Divergence [108.28566246421742]
  This paper develops a dimensionality reduction method that allows us to move the optimization to a finite-dimensional setting with an explicit bound on the dimension. In order to make progress on the problem, we restrict ourselves to Bayesian risks induced by a relatively large class of loss functions, namely Bregman divergences.
  arXiv  Detail & Related papers  (2022-02-23T16:22:28Z)
• 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)
• Robust Mean Estimation in High Dimensions via $\ell_0$ Minimization [21.65637588606572]
  We study the robust mean estimation problem in high dimensions, where $alpha 0.5$ fraction of the data points can be arbitrarily corrupted. Motivated by compressive sensing, we formulate the robust mean estimation problem as the minimization of the $ell_p$ $(0p1)$. Both synthetic and real data experiments demonstrate that the proposed algorithms significantly outperform state-of-the-art robust mean estimation methods.
  arXiv  Detail & Related papers  (2020-08-21T00:19:48Z)
• On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization [55.937424268654645]
  We consider algorithm-independent lower bounds for the problem of black-box optimization of functions having a bounded norm. We provide a novel proof technique for deriving lower bounds on the regret, with benefits including simplicity, versatility, and an improved dependence on the error probability.
  arXiv  Detail & Related papers  (2020-08-20T03:48:14Z)
• Learning Minimax Estimators via Online Learning [55.92459567732491]
  We consider the problem of designing minimax estimators for estimating parameters of a probability distribution. We construct an algorithm for finding a mixed-case Nash equilibrium.
  arXiv  Detail & Related papers  (2020-06-19T22:49:42Z)

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.