Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It

• URL: http://arxiv.org/abs/2404.15084v1
• Date: Tue, 23 Apr 2024 14:34:16 GMT
• Title: Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It
• Authors: Yuta Saito, Masahiro Nomura,
• Abstract summary: We show that naively applying an unbiased estimator of the generalization performance as a surrogate objective in HPO can cause an unexpected failure. We propose simple and computationally efficient corrections to the typical HPO procedure to deal with the aforementioned issues simultaneously.
• Score: 20.312864152544954
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There has been a growing interest in off-policy evaluation in the literature such as recommender systems and personalized medicine. We have so far seen significant progress in developing estimators aimed at accurately estimating the effectiveness of counterfactual policies based on biased logged data. However, there are many cases where those estimators are used not only to evaluate the value of decision making policies but also to search for the best hyperparameters from a large candidate space. This work explores the latter hyperparameter optimization (HPO) task for off-policy learning. We empirically show that naively applying an unbiased estimator of the generalization performance as a surrogate objective in HPO can cause an unexpected failure, merely pursuing hyperparameters whose generalization performance is greatly overestimated. We then propose simple and computationally efficient corrections to the typical HPO procedure to deal with the aforementioned issues simultaneously. Empirical investigations demonstrate the effectiveness of our proposed HPO algorithm in situations where the typical procedure fails severely.

Related papers

• Hierarchical Preference Optimization: Learning to achieve goals via feasible subgoals prediction [71.81851971324187]
  This work introduces Hierarchical Preference Optimization (HPO), a novel approach to hierarchical reinforcement learning (HRL) HPO addresses non-stationarity and infeasible subgoal generation issues when solving complex robotic control tasks. Experiments on challenging robotic navigation and manipulation tasks demonstrate impressive performance of HPO, where it shows an improvement of up to 35% over the baselines.
  arXiv  Detail & Related papers  (2024-11-01T04:58:40Z)
• Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation [46.61909578101735]
  Adversarial Policy Optimization (AdvPO) is a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback. In this paper, we introduce a lightweight way to quantify uncertainties in rewards, relying solely on the last layer embeddings of the reward model.
  arXiv  Detail & Related papers  (2024-03-08T09:20:12Z)
• Probabilistic Offline Policy Ranking with Approximate Bayesian Computation [4.919605764492689]
  It is essential to compare and rank candidate policies offline before real-world deployment for safety and reliability. We present Probabilistic Offline Policy Ranking (POPR), a framework to address OPR problems. POPR does not rely on value estimation, and the derived performance posterior can be used to distinguish candidates in worst, best, and average-cases.
  arXiv  Detail & Related papers  (2023-12-17T05:22:44Z)
• Fine-Tuning Language Models with Advantage-Induced Policy Alignment [80.96507425217472]
  We propose a novel algorithm for aligning large language models to human preferences. We show that it consistently outperforms PPO in language tasks by a large margin. We also provide a theoretical justification supporting the design of our loss function.
  arXiv  Detail & Related papers  (2023-06-04T01:59:40Z)
• Prediction-Oriented Bayesian Active Learning [51.426960808684655]
  Expected predictive information gain (EPIG) is an acquisition function that measures information gain in the space of predictions rather than parameters. EPIG leads to stronger predictive performance compared with BALD across a range of datasets and models.
  arXiv  Detail & Related papers  (2023-04-17T10:59:57Z)
• Uncertainty-Aware Instance Reweighting for Off-Policy Learning [63.31923483172859]
  We propose a Uncertainty-aware Inverse Propensity Score estimator (UIPS) for improved off-policy learning. Experiment results on synthetic and three real-world recommendation datasets demonstrate the advantageous sample efficiency of the proposed UIPS estimator.
  arXiv  Detail & Related papers  (2023-03-11T11:42:26Z)
• Quantile Off-Policy Evaluation via Deep Conditional Generative Learning [21.448553360543478]
  Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy. We propose a doubly-robust inference procedure for quantile OPE in sequential decision making. We demonstrate the advantages of this proposed estimator through both simulations and a real-world dataset from a short-video platform.
  arXiv  Detail & Related papers  (2022-12-29T22:01:43Z)
• Off-policy evaluation for learning-to-rank via interpolating the item-position model and the position-based model [83.83064559894989]
  A critical need for industrial recommender systems is the ability to evaluate recommendation policies offline, before deploying them to production. We develop a new estimator that mitigates the problems of the two most popular off-policy estimators for rankings. In particular, the new estimator, called INTERPOL, addresses the bias of a potentially misspecified position-based model.
  arXiv  Detail & Related papers  (2022-10-15T17:22:30Z)
• Evaluating the Robustness of Off-Policy Evaluation [10.760026478889664]
  Off-policy Evaluation (OPE) evaluates the performance of hypothetical policies leveraging only offline log data. It is particularly useful in applications where the online interaction involves high stakes and expensive setting. We develop Interpretable Evaluation for Offline Evaluation (IEOE), an experimental procedure to evaluate OPE estimators' robustness.
  arXiv  Detail & Related papers  (2021-08-31T09:33:13Z)
• Cost-Efficient Online Hyperparameter Optimization [94.60924644778558]
  We propose an online HPO algorithm that reaches human expert-level performance within a single run of the experiment. Our proposed online HPO algorithm reaches human expert-level performance within a single run of the experiment, while incurring only modest computational overhead compared to regular training.
  arXiv  Detail & Related papers  (2021-01-17T04:55:30Z)

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.