Related papers: Sharpness-Aware Black-Box Optimization

Sharpness-Aware Black-Box Optimization

URL: http://arxiv.org/abs/2410.12457v1
Date: Wed, 16 Oct 2024 11:08:06 GMT
Title: Sharpness-Aware Black-Box Optimization
Authors: Feiyang Ye, Yueming Lyu, Xuehao Wang, Masashi Sugiyama, Yu Zhang, Ivor Tsang,
Abstract summary: We propose a Sharpness-Aware Black-box Optimization (SABO) algorithm, which applies a sharpness-aware minimization strategy to improve the model generalization. Empirically, extensive experiments on the black-box prompt fine-tuning tasks demonstrate the effectiveness of the proposed SABO method in improving model generalization performance.
Score: 47.95184866255126
License:
Abstract: Black-box optimization algorithms have been widely used in various machine learning problems, including reinforcement learning and prompt fine-tuning. However, directly optimizing the training loss value, as commonly done in existing black-box optimization methods, could lead to suboptimal model quality and generalization performance. To address those problems in black-box optimization, we propose a novel Sharpness-Aware Black-box Optimization (SABO) algorithm, which applies a sharpness-aware minimization strategy to improve the model generalization. Specifically, the proposed SABO method first reparameterizes the objective function by its expectation over a Gaussian distribution. Then it iteratively updates the parameterized distribution by approximated stochastic gradients of the maximum objective value within a small neighborhood around the current solution in the Gaussian distribution space. Theoretically, we prove the convergence rate and generalization bound of the proposed SABO algorithm. Empirically, extensive experiments on the black-box prompt fine-tuning tasks demonstrate the effectiveness of the proposed SABO method in improving model generalization performance.

Related papers

Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation [60.41803046775034]
We show how to perform user-preferred targeted generation via diffusion models with only black-box target scores of users. Experiments on both numerical test problems and target-guided 3D-molecule generation tasks show the superior performance of our method in achieving better target scores.
arXiv Detail & Related papers (2024-06-02T17:26:27Z)
Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration [2.984929040246293]
novel noise-free Bayesian optimization strategies that rely on a random exploration step to enhance the accuracy of Gaussian process surrogate models. New algorithms retain the ease of implementation of the classical GP-UCB, but an additional exploration step facilitates their convergence.
arXiv Detail & Related papers (2024-01-30T14:16:06Z)
Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models [88.80146574509195]
Quantization is a promising approach for reducing memory overhead and accelerating inference. We propose a novel-aware quantization (ZSAQ) framework for the zero-shot quantization of various PLMs.
arXiv Detail & Related papers (2023-10-20T07:09:56Z)
Polynomial-Model-Based Optimization for Blackbox Objectives [0.0]
Black-box optimization seeks to find optimal parameters for systems such that a pre-defined objective function is minimized. PMBO is a novel blackbox that finds the minimum by fitting a surrogate to the objective function. PMBO is benchmarked against other state-of-the-art algorithms for a given set of artificial, analytical functions.
arXiv Detail & Related papers (2023-09-01T14:11:03Z)
Neural-BO: A Black-box Optimization Algorithm using Deep Neural Networks [12.218039144209017]
We propose a novel black-box optimization algorithm where the black-box function is modeled using a neural network. Our algorithm does not need a Bayesian neural network to estimate predictive uncertainty and is therefore computationally favorable.
arXiv Detail & Related papers (2023-03-03T02:53:56Z)
Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces [54.58348769621782]
Tree ensembles can be well-suited for black-box optimization tasks such as algorithm tuning and neural architecture search. Two well-known challenges in using tree ensembles for black-box optimization are (i) effectively quantifying model uncertainty for exploration and (ii) optimizing over the piece-wise constant acquisition function. Our framework performs as well as state-of-the-art methods for unconstrained black-box optimization over continuous/discrete features and outperforms competing methods for problems combining mixed-variable feature spaces and known input constraints.
arXiv Detail & Related papers (2022-07-02T16:59:37Z)
Meta Learning Black-Box Population-Based Optimizers [0.0]
We propose the use of meta-learning to infer population-based blackbox generalizations. We show that the meta-loss function encourages a learned algorithm to alter its search behavior so that it can easily fit into a new context.
arXiv Detail & Related papers (2021-03-05T08:13:25Z)
Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
arXiv Detail & Related papers (2020-12-21T17:29:58Z)
Global Optimization of Gaussian processes [52.77024349608834]
We propose a reduced-space formulation with trained Gaussian processes trained on few data points. The approach also leads to significantly smaller and computationally cheaper sub solver for lower bounding. In total, we reduce time convergence by orders of orders of the proposed method.
arXiv Detail & Related papers (2020-05-21T20:59:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.