An Empirical Study of Assumptions in Bayesian Optimisation

• URL: http://arxiv.org/abs/2012.03826v3
• Date: Fri, 12 Feb 2021 09:15:59 GMT
• Title: An Empirical Study of Assumptions in Bayesian Optimisation
• Authors: Alexander I. Cowen-Rivers, Wenlong Lyu, Rasul Tutunov, Zhi Wang, Antoine Grosnit, Ryan Rhys Griffiths, Hao Jianye, Jun Wang, Haitham Bou Ammar
• Abstract summary: In this work we rigorously analyse conventional and non-conventional assumptions inherent to Bayesian optimisation. We conclude that the majority of hyper- parameter tuning tasks exhibit heteroscedasticity and non-stationarity. We hope these findings may serve as guiding principles, both for practitioners and for further research in the field.
• Score: 61.19427472792523
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inspired by the increasing desire to efficiently tune machine learning hyper-parameters, in this work we rigorously analyse conventional and non-conventional assumptions inherent to Bayesian optimisation. Across an extensive set of experiments we conclude that: 1) the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, 2) multi-objective acquisition ensembles with Pareto-front solutions significantly improve queried configurations, and 3) robust acquisition maximisation affords empirical advantages relative to its non-robust counterparts. We hope these findings may serve as guiding principles, both for practitioners and for further research in the field.

Related papers

• Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation [10.77641869521259]
  CMOBO balances learning of the feasible region with multi-objective optimization within the feasible region in a principled manner. We provide both theoretical justification and empirical evidence, demonstrating the efficacy of our approach on various synthetic benchmarks and real-world applications.
  arXiv  Detail & Related papers  (2024-11-06T03:38:00Z)
• See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition [56.87609859444084]
  parameter-efficient fine-tuning (PEFT) focuses on optimizing a select subset of parameters while keeping the rest fixed, significantly lowering computational and storage overheads. We take the first step to unify all approaches by dissecting them from a decomposition perspective. We introduce two novel PEFT methods alongside a simple yet effective framework designed to enhance the performance of PEFT techniques across various applications.
  arXiv  Detail & Related papers  (2024-07-07T15:44:42Z)
• Combining Automated Optimisation of Hyperparameters and Reward Shape [7.407166175374958]
  We propose a methodology for the combined optimisation of hyperparameters and the reward function. We conducted extensive experiments using Proximal Policy optimisation and Soft Actor-Critic. Our results show that combined optimisation significantly improves over baseline performance in half of the environments and achieves competitive performance in the others.
  arXiv  Detail & Related papers  (2024-06-26T12:23:54Z)
• Inverse Reinforcement Learning with Sub-optimal Experts [56.553106680769474]
  We study the theoretical properties of the class of reward functions that are compatible with a given set of experts. Our results show that the presence of multiple sub-optimal experts can significantly shrink the set of compatible rewards. We analyze a uniform sampling algorithm that results in being minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to the one of the optimal agent.
  arXiv  Detail & Related papers  (2024-01-08T12:39:25Z)
• Expert-guided Bayesian Optimisation for Human-in-the-loop Experimental Design of Known Systems [0.0]
  We apply high- throughput (batch) Bayesian optimisation alongside anthropological decision theory to enable domain experts to influence the selection of optimal experiments. Our methodology exploits the hypothesis that humans are better at making discrete choices than continuous ones and enables experts to influence critical early decisions.
  arXiv  Detail & Related papers  (2023-12-05T16:09:31Z)
• Modeling the Machine Learning Multiverse [10.809039816152161]
  We present a principled framework for making robust and generalizable claims in machine learning research. Our framework builds upon the psychology Multiverse Analysis introduced in response to psychology's own crisis. For the machine learning community, the Multiverse Analysis is a simple and effective technique for identifying robust claims.
  arXiv  Detail & Related papers  (2022-06-13T09:11:48Z)
• Optimizer Amalgamation [124.33523126363728]
  We are motivated to study a new problem named Amalgamation: how can we best combine a pool of "teacher" amalgamations into a single "student" that can have stronger problem-specific performance? First, we define three differentiable mechanisms to amalgamate a pool of analyticals by gradient descent. In order to reduce variance of the process, we also explore methods to stabilize the process by perturbing the target.
  arXiv  Detail & Related papers  (2022-03-12T16:07:57Z)
• What Makes an Effective Scalarising Function for Multi-Objective Bayesian Optimisation? [6.4239565988811425]
  Multi-objective Bayesian optimisation by scalarising the objectives avoids the computation of expensive integral-based acquisition functions. The effectiveness of all the methodological improvements defined here is demonstrated on a real-world problem.
  arXiv  Detail & Related papers  (2021-04-10T15:18:58Z)
• Are we Forgetting about Compositional Optimisers in Bayesian Optimisation? [66.39551991177542]
  This paper presents a sample methodology for global optimisation. Within this, a crucial performance-determiningtrivial is maximising the acquisition function. We highlight the empirical advantages of the approach to optimise functionation across 3958 individual experiments.
  arXiv  Detail & Related papers  (2020-12-15T12:18:38Z)
• Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling [58.56638141701966]
  Experimenters can often acquire the knowledge about the location of the global optimum. It is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization. An efficient Bayesian optimization approach has been proposed via posterior sampling on the posterior distribution of the global optimum.
  arXiv  Detail & Related papers  (2020-02-26T01:57:36Z)

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.