Parameter-Free Algorithms for Performative Regret Minimization under Decision-Dependent Distributions

• URL: http://arxiv.org/abs/2402.15188v1
• Date: Fri, 23 Feb 2024 08:36:28 GMT
• Title: Parameter-Free Algorithms for Performative Regret Minimization under Decision-Dependent Distributions
• Authors: Sungwoo Park, Junyeop Kwon, Byeongnoh Kim, Suhyun Chae, Jeeyong Lee, Dabeen Lee
• Abstract summary: performative risk minimization is a formulation of optimization under decision-dependent distributions. Our algorithms significantly improve upon existing Lipschitz constant distribution parameter-based methods. We provide experimental results that demonstrate the numerical superiority of our algorithms over the existing method and other black-box optimistic optimization methods.
• Score: 15.396561118589577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper studies performative risk minimization, a formulation of stochastic optimization under decision-dependent distributions. We consider the general case where the performative risk can be non-convex, for which we develop efficient parameter-free optimistic optimization-based methods. Our algorithms significantly improve upon the existing Lipschitz bandit-based method in many aspects. In particular, our framework does not require knowledge about the sensitivity parameter of the distribution map and the Lipshitz constant of the loss function. This makes our framework practically favorable, together with the efficient optimistic optimization-based tree-search mechanism. We provide experimental results that demonstrate the numerical superiority of our algorithms over the existing method and other black-box optimistic optimization methods.

Related papers

• Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms [13.134564730161983]
  This paper adopts a novel approach to deep learning optimization, focusing on gradient descent (SGD) and its variants. We show that SGD and its variants demonstrate performance on par with flat-minimas like SAM, albeit with half the gradient evaluations. Our study uncovers several key findings regarding the relationship between training loss and hold-out accuracy, as well as the comparable performance of SGD and noise-enabled variants.
  arXiv  Detail & Related papers  (2024-03-01T14:55:22Z)
• Multistage Stochastic Optimization via Kernels [3.7565501074323224]
  We develop a non-parametric, data-driven, tractable approach for solving multistage optimization problems. We show that the proposed method produces decision rules with near-optimal average performance.
  arXiv  Detail & Related papers  (2023-03-11T23:19:32Z)
• Generalizing Bayesian Optimization with Decision-theoretic Entropies [102.82152945324381]
  We consider a generalization of Shannon entropy from work in statistical decision theory. We first show that special cases of this entropy lead to popular acquisition functions used in BO procedures. We then show how alternative choices for the loss yield a flexible family of acquisition functions.
  arXiv  Detail & Related papers  (2022-10-04T04:43:58Z)
• Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares [68.8204255655161]
  We consider potentially non- optimized approximation problems. In this paper, we propose an algorithm that achieves close to optimal a priori computational guarantees.
  arXiv  Detail & Related papers  (2022-04-11T09:37:04Z)
• Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization [23.359363844344408]
  We introduce an algorithm framework of managing the interaction between optimization error flux and statistical error flux evolving in the optimization process. Our framework and its analysis can be applied to a large family of functions and partitions that satisfy different local smoothness assumptions. In theory, we prove the algorithm enjoys rate-optimal regret bounds under different local smoothness assumptions.
  arXiv  Detail & Related papers  (2021-06-17T02:37:39Z)
• On the Optimality of Batch Policy Optimization Algorithms [106.89498352537682]
  Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. We show that any confidence-adjusted index algorithm is minimax optimal, whether it be optimistic, pessimistic or neutral. We introduce a new weighted-minimax criterion that considers the inherent difficulty of optimal value prediction.
  arXiv  Detail & Related papers  (2021-04-06T05:23:20Z)
• Recent Theoretical Advances in Non-Convex Optimization [56.88981258425256]
  Motivated by recent increased interest in analysis of optimization algorithms for non- optimization in deep networks and other problems in data, we give an overview of recent results of theoretical optimization algorithms for non- optimization.
  arXiv  Detail & Related papers  (2020-12-11T08:28:51Z)
• Soft-Robust Algorithms for Batch Reinforcement Learning [36.78967245470449]
  In reinforcement learning, robust decision-making problems with limited data are usually computed by the percentile criterion. We show that the percentile criterion is non- theoretical as it is difficult to optimize and ignores the mean performance. We propose and analyze two algorithms to approximately optimize the percentile criterion.
  arXiv  Detail & Related papers  (2020-11-30T01:36:16Z)
• Logistic Q-Learning [87.00813469969167]
  We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The main feature of our algorithm is a convex loss function for policy evaluation that serves as a theoretically sound alternative to the widely used squared Bellman error.
  arXiv  Detail & Related papers  (2020-10-21T17:14:31Z)
• Stochastic Optimization Forests [60.523606291705214]
  We show how to train forest decision policies by growing trees that choose splits to directly optimize the downstream decision quality, rather than splitting to improve prediction accuracy as in the standard random forest algorithm. We show that our approximate splitting criteria can reduce running time hundredfold, while achieving performance close to forest algorithms that exactly re-optimize for every candidate split.
  arXiv  Detail & Related papers  (2020-08-17T16:56:06Z)

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.