Relaxing the I.I.D. Assumption: Adaptively Minimax Optimal Regret via Root-Entropic Regularization

• URL: http://arxiv.org/abs/2007.06552v3
• Date: Fri, 22 Jul 2022 03:25:19 GMT
• Title: Relaxing the I.I.D. Assumption: Adaptively Minimax Optimal Regret via Root-Entropic Regularization
• Authors: Blair Bilodeau, Jeffrey Negrea, Daniel M. Roy
• Abstract summary: We consider prediction with expert advice when data are generated from varying arbitrarily within an unknown constraint set. The Hedge algorithm was recently shown to be simultaneously minimax optimal for i.i.d. data. We provide matching upper and lower bounds on the minimax regret at all levels, show that Hedge with deterministic learning rates is suboptimal outside of the extremes, and prove that one can adaptively obtain minimax regret at all levels.
• Score: 16.536558038560695
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider prediction with expert advice when data are generated from distributions varying arbitrarily within an unknown constraint set. This semi-adversarial setting includes (at the extremes) the classical i.i.d. setting, when the unknown constraint set is restricted to be a singleton, and the unconstrained adversarial setting, when the constraint set is the set of all distributions. The Hedge algorithm -- long known to be minimax (rate) optimal in the adversarial regime -- was recently shown to be simultaneously minimax optimal for i.i.d. data. In this work, we propose to relax the i.i.d. assumption by seeking adaptivity at all levels of a natural ordering on constraint sets. We provide matching upper and lower bounds on the minimax regret at all levels, show that Hedge with deterministic learning rates is suboptimal outside of the extremes, and prove that one can adaptively obtain minimax regret at all levels. We achieve this optimal adaptivity using the follow-the-regularized-leader (FTRL) framework, with a novel adaptive regularization scheme that implicitly scales as the square root of the entropy of the current predictive distribution, rather than the entropy of the initial predictive distribution. Finally, we provide novel technical tools to study the statistical performance of FTRL along the semi-adversarial spectrum.

Related papers

• Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints [29.514323697659613]
  We address a generalization of the bandit with knapsacks problem, where a learner aims to maximize rewards while satisfying an arbitrary set of long-term constraints. Our goal is to design best-of-both-worlds algorithms that perform under both and adversarial constraints.
  arXiv  Detail & Related papers  (2024-05-25T08:09:36Z)
• Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression [12.443289202402761]
  We show the benefits of batch- partitioning through the lens of a minimum-norm overparametrized linear regression model. We characterize the optimal batch size and show it is inversely proportional to the noise level. We also show that shrinking the batch minimum-norm estimator by a factor equal to the Weiner coefficient further stabilizes it and results in lower quadratic risk in all settings.
  arXiv  Detail & Related papers  (2023-06-14T11:02:08Z)
• Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization [52.7137956951533]
  We argue that devising simpler methods for learning predictors on existing features is a promising direction for future research. We introduce Domain-Adjusted Regression (DARE), a convex objective for learning a linear predictor that is provably robust under a new model of distribution shift. Under a natural model, we prove that the DARE solution is the minimax-optimal predictor for a constrained set of test distributions.
  arXiv  Detail & Related papers  (2022-02-14T16:42:16Z)
• Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers [31.102181563065844]
  Quantile (and, more generally, KL) regret bounds relax the goal of competing against the best individual expert to only competing against a majority of experts on adversarial data. More recently, the semi-adversarial paradigm (Bilodeau, Negrea, and Roy 2020) provides an alternative relaxation of adversarial online learning by considering data that may be neither fully adversarial nor adversarial. We achieve the minimax optimal regret in both paradigms using FTRL with separate, novel, root-logarithmic regularizers, both of which can be interpreted as yielding variants of NormalHedge.
  arXiv  Detail & Related papers  (2021-10-27T22:38:52Z)
• Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation [154.2195491708548]
  We study the prediction discriminability and diversity by studying the structure of the classification output matrix of a randomly selected data batch. We propose Batch Nuclear-norm Maximization and Minimization, which performs nuclear-norm on the target output matrix to enhance the target prediction ability. Experiments show that our method could boost the adaptation accuracy and robustness under three typical domain adaptation scenarios.
  arXiv  Detail & Related papers  (2021-07-13T15:08:32Z)
• Near-optimal inference in adaptive linear regression [60.08422051718195]
  Even simple methods like least squares can exhibit non-normal behavior when data is collected in an adaptive manner. We propose a family of online debiasing estimators to correct these distributional anomalies in at least squares estimation. We demonstrate the usefulness of our theory via applications to multi-armed bandit, autoregressive time series estimation, and active learning with exploration.
  arXiv  Detail & Related papers  (2021-07-05T21:05:11Z)
• Optimal Stochastic Nonconvex Optimization with Bandit Feedback [45.675080529219365]
  We analyze continuous armed bandit problems for non cost functions under certain smoothness and sublevel set assumptions. We then propose an adaptive splitting method, which can significantly improve the performance.
  arXiv  Detail & Related papers  (2021-03-30T05:21:12Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)
• Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems [120.21685755278509]
  In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster in time up to an error. Rather than fixing the minibatch the step-size at the outset, we propose to allow parameters to evolve adaptively.
  arXiv  Detail & Related papers  (2020-07-02T16:02:02Z)
• A Convergent and Dimension-Independent Min-Max Optimization Algorithm [32.492526162436405]
  We show that a distribution which the min-player uses to update its parameters depends on a smooth and bounded nonnon-concave function. Our algorithm converges to an approximate local equilibrium in a number of iterations that does not depend on the iterations.
  arXiv  Detail & Related papers  (2020-06-22T16:11:30Z)
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment [52.02794488304448]
  We propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.
  arXiv  Detail & Related papers  (2020-03-26T22:10:04Z)

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.