The choices of hyperparameters have critical effects on the performance of machine learning models. In this paper, we present a general framework that is able to construct an adaptive optimizer, which automatically adjust the appropriate algorithm and parameters in the process of optimization. Examining the method of adaptive optimizer, we product an example of using genetic algorithm to construct an adaptive optimizer based on Bayesian Optimizer and compared effectiveness with original optimizer. Especially, It has great advantages in parallel optimization.
Practical results have shown that deep learning optimizers using small constant learning rates, hyperparameters close to one, and large batch sizes can find the model parameters of deep neural networks that minimize the loss functions. We first show theoretical evidence that the momentum method (Momentum) and adaptive moment estimation (Adam) perform well in the sense that the upper bound of the theoretical performance measure is small with a small constant learning rate, hyperparameters close to one, and a large batch size. Next, we show that there exists a batch size called the critical batc…
Idiap Research Institute（伊迪亚普研究所）；EPFL（洛桑联邦理工学院）；University of Geneva（日内瓦大学）
The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under near-optimal problem-specific hyperparameters, and finding these settings may be prohibitively costly for practitioners. In this work, we argue that a fair assessment of optimizers' performance must take the computational cost of hyperparameter tuning into account, i.e., how easy it is to find good hyperparameter configurations using an automatic hyperparameter search. Evaluating a variety of optimizers on an extensiv…
Department of Computer Science, UCLA（加州大学洛杉矶分校计算机科学系）；Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）；Google Research（谷歌研究院）
Many optimizers have been proposed for training deep neural networks, and they often have multiple hyperparameters, which make it tricky to benchmark their performance. In this work, we propose a new benchmarking protocol to evaluate both end-to-end efficiency (training a model from scratch without knowing the best hyperparameter) and data-addition training efficiency (the previously selected hyperparameters are used for periodically re-training the model with newly collected data). For end-to-end efficiency, unlike previous work that assumes random hyperparameter tuning, which over-emphasizes…
Hyperparameter optimization is a ubiquitous challenge in machine learning, and the performance of a trained model depends crucially upon their effective selection. While a rich set of tools exist for this purpose, there are currently no practical hyperparameter selection methods under the constraint of differential privacy (DP). We study honest hyperparameter selection for differentially private machine learning, in which the process of hyperparameter tuning is accounted for in the overall privacy budget. To this end, we i) show that standard composition tools outperform more advanced techniqu…
Google Research（谷歌研究院）；Vector Institute（向量研究所）；University of Toronto（多伦多大学）；DeepMind（深度思维）；Institute for Advanced Study（普林斯顿高等研究院）
Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the hyperparameter tuning protocol. Our findings suggest that the hyperparameter search space may be the single most important factor explaining the rankings obtained by recent empirical comparisons in the literature. In fact, we show that these results can be contradicted when hyperparameter search spaces are changed. As tuning effort grows without bound, more general optimizers should never underperform the ones they can approximate (i…
University of Freiburg（弗莱堡大学）；Leibniz University Hannover（汉诺威莱布尼茨大学）；Leiden University（莱顿大学）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Bosch Center for Artificial Intelligence（博世人工智能中心）
In this short note, we describe our submission to the NeurIPS 2020 BBO challenge. Motivated by the fact that different optimizers work well on different problems, our approach switches between different optimizers. Since the team names on the competition's leaderboard were randomly generated "alliteration nicknames", consisting of an adjective and an animal with the same initial letter, we called our approach the Switching Squirrel, or here, short, Squirrel.
Working with any gradient-based machine learning algorithm involves the tedious task of tuning the optimizer's hyperparameters, such as its step size. Recent work has shown how the step size can itself be optimized alongside the model parameters by manually deriving expressions for "hypergradients" ahead of time. We show how to automatically compute hypergradients with a simple and elegant modification to backpropagation. This allows us to easily apply the method to other optimizers and hyperparameters (e.g. momentum coefficients). We can even recursively apply the method to its own hyper-hype…
Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
University of Basel（巴塞尔大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；Tübingen AI Center（图宾根人工智能中心）
Meta-learning hyperparameter optimization (HPO) algorithms from prior experiments is a promising approach to improve optimization efficiency over objective functions from a similar distribution. However, existing methods are restricted to learning from experiments sharing the same set of hyperparameters. In this paper, we introduce the OptFormer, the first text-based Transformer HPO framework that provides a universal end-to-end interface for jointly learning policy and function prediction when trained on vast tuning data from the wild, such as Google's Vizier database, one of the world's larg…
Centro de Informática (CIn), Universidade Federal de Pernambuco (UFPE)（伯南布哥联邦大学信息中心（CIn））
Proper optimization of deep neural networks is an open research question since an optimal procedure to change the learning rate throughout training is still unknown. Manually defining a learning rate schedule involves troublesome time-consuming try and error procedures to determine hyperparameters such as learning rate decay epochs and learning rate decay rates. Although adaptive learning rate optimizers automatize this process, recent studies suggest they may produce overffiting and reduce performance when compared to fine-tuned learning rate schedules. Considering that deep neural networks l…
Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
Basic Research of Artificial Intelligence Laboratory（人工智能基础研究实验室）；Federated Learning Problems Laboratory（联邦学习问题实验室）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Innopolis University（因诺普里斯大学）
carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks
Leibniz University Hannover（汉诺威莱布尼茨大学）；Albert-Ludwigs University Freiburg（弗赖堡阿尔伯特-路易斯大学）；University of St Andrews（圣安德鲁大学）；Sorbonne Université Paris（巴黎索邦大学）；LMU Munich（慕尼黑路德维希-马克西米利安大学）；University of Tübingen（图宾根大学）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；L3S Research Center（L3S研究中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Ludwig-Maximilians-Universität München（慕尼黑大学）；University of Wyoming（怀俄明大学）
Automated hyperparameter optimization (HPO) has gained great popularity and is an important ingredient of most automated machine learning frameworks. The process of designing HPO algorithms, however, is still an unsystematic and manual process: Limitations of prior work are identified and the improvements proposed are -- even though guided by expert knowledge -- still somewhat arbitrary. This rarely allows for gaining a holistic understanding of which algorithmic components are driving performance, and carries the risk of overlooking good algorithmic design choices. We present a principled app…
We propose ActiveLR, an optimization meta algorithm that localizes the learning rate, $α$, and adapts them at each epoch according to whether the gradient at each epoch changes sign or not. This sign-conscious algorithm is aware of whether from the previous step to the current one the update of each parameter has been too large or too small and adjusts the $α$ accordingly. We implement the Active version (ours) of widely used and recently published gradient descent optimizers, namely SGD with momentum, AdamW, RAdam, and AdaBelief. Our experiments on ImageNet, CIFAR-10, WikiText-103, WikiText-2…
Adaptive Moment Estimation (ADAM) is a very popular training algorithm for deep neural networks and belongs to the family of adaptive gradient descent optimizers. However to the best of the authors knowledge no complete convergence analysis exists for ADAM. The contribution of this paper is a method for the local convergence analysis in batch mode for a deterministic fixed training set, which gives necessary conditions for the hyperparameters of the ADAM algorithm. Due to the local nature of the arguments the objective function can be non-convex but must be at least twice continuously differen…
In this paper, we describe our method for tackling the automated hyperparameter optimization challenge in QQ Browser 2021 AI Algorithm Competiton (ACM CIKM 2021 AnalyticCup Track 2). The competition organizers provide anonymized realistic industrial tasks and datasets for black-box optimization. Based on our open-sourced package OpenBox, we adopt the Bayesian optimization framework for configuration sampling and a heuristic early stopping strategy. We won first place in both the preliminary and final contests with the results of 0.938291 and 0.918753, respectively.
Much as replacing hand-designed features with learned functions has revolutionized how we solve perceptual tasks, we believe learned algorithms will transform how we train models. In this work we focus on general-purpose learned optimizers capable of training a wide variety of problems with no user-specified hyperparameters. We introduce a new, neural network parameterized, hierarchical optimizer with access to additional features such as validation loss to enable automatic regularization. Most learned optimizers have been trained on only a single task, or a small number of tasks. We train our…
JD Finance America Corporation（京东金融美国公司）；University of Pittsburgh（匹兹堡大学）；Nanjing University of Information Science & Technology（南京信息工程大学）
Modern machine learning algorithms usually involve tuning multiple (from one to thousands) hyperparameters which play a pivotal role in terms of model generalizability. Black-box optimization and gradient-based algorithms are two dominant approaches to hyperparameter optimization while they have totally distinct advantages. How to design a new hyperparameter optimization technique inheriting all benefits from both approaches is still an open problem. To address this challenging problem, in this paper, we propose a new hyperparameter optimization method with zeroth-order hyper-gradients (HOZOG)…
LMU Munich（慕尼黑大学）；TU Dresden（德累斯顿工业大学）；University of Münster（明斯特大学）；University of Twente（特文特大学）
Hyperparameter optimization (HPO) is a key component of machine learning models for achieving peak predictive performance. While numerous methods and algorithms for HPO have been proposed over the last years, little progress has been made in illuminating and examining the actual structure of these black-box optimization problems. Exploratory landscape analysis (ELA) subsumes a set of techniques that can be used to gain knowledge about properties of unknown optimization problems. In this paper, we evaluate the performance of five different black-box optimizers on 30 HPO problems, which consist …
Conventional optimization methods in machine learning and controls rely heavily on first-order update rules. Selecting the right method and hyperparameters for a particular task often involves trial-and-error or practitioner intuition, motivating the field of meta-learning. We generalize a broad family of preexisting update rules by proposing a meta-learning framework in which the inner loop optimization step involves solving a differentiable convex optimization (DCO). We illustrate the theoretical appeal of this approach by showing that it enables one-step optimization of a family of linear l…
As machine learning permeates more industries and models become more expensive and time consuming to train, the need for efficient automated hyperparameter optimization (HPO) has never been more pressing. Multi-step planning based approaches to hyperparameter optimization promise improved efficiency over myopic alternatives by more effectively balancing out exploration and exploitation. However, the potential of these approaches has not been fully realized due to their technical complexity and computational intensity. In this work, we leverage recent advances in Transformer-based, natural-lang…
Wayfair；North Carolina State University（北卡罗来纳州立大学）
How can we make software analytics simpler and faster? One method is to match the complexity of analysis to the intrinsic complexity of the data being explored. For example, hyperparameter optimizers find the control settings for data miners that improve the predictions generated via software analytics. Sometimes, very fast hyperparameter optimization can be achieved by "DODGE-ing"; i.e. simply steering way from settings that lead to similar conclusions. But when is it wise to use that simple approach and when must we use more complex (and much slower) optimizers?} To answer this, we applied h…
Twitter（推特）；Facebook（脸书）；SigOpt, an Intel company（SigOpt（英特尔公司旗下））；Valohai；Paradigm（第四范式）；ChaLearn
This paper presents the results and insights from the black-box optimization (BBO) challenge at NeurIPS 2020 which ran from July-October, 2020. The challenge emphasized the importance of evaluating derivative-free optimizers for tuning the hyperparameters of machine learning models. This was the first black-box optimization challenge with a machine learning emphasis. It was based on tuning (validation set) performance of standard machine learning models on real datasets. This competition has widespread impact as black-box optimization (e.g., Bayesian optimization) is relevant for hyperparamete…
One of the most popular training algorithms for deep neural networks is the Adaptive Moment Estimation (Adam) introduced by Kingma and Ba. Despite its success in many applications there is no satisfactory convergence analysis: only local convergence can be shown for batch mode under some restrictions on the hyperparameters, counterexamples exist for incremental mode. Recent results show that for simple quadratic objective functions limit cycles of period 2 exist in batch mode, but only for atypical hyperparameters, and only for the algorithm without bias correction. %More general there are sev…
AutoOptLib: Tailoring Metaheuristic Optimizers via Automated Algorithm Design
Southern University of Science and Technology（南方科技大学）；Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology（南方科技大学可信自主系统研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
The PC algorithm infers causal relations using conditional independence tests that require a pre-specified Type I $α$ level. PC is however unsupervised, so we cannot tune $α$ using traditional cross-validation. We therefore propose AutoPC, a fast procedure that optimizes $α$ directly for a user chosen metric. We in particular force PC to double check its output by executing a second run on the recovered graph. We choose the final output as the one which maximizes stability between the two runs. AutoPC consistently outperforms the state of the art across multiple metrics.
While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimi…
We propose a new, more general approach to the design of stochastic gradient-based optimization methods for machine learning. In this new framework, optimizers assume access to a batch of gradient estimates per iteration, rather than a single estimate. This better reflects the information that is actually available in typical machine learning setups. To demonstrate the usefulness of this generalized approach, we develop Eve, an adaptation of the Adam optimizer which uses examplewise gradients to obtain more accurate second-moment estimates. We provide preliminary experiments, without hyperpara…
James Cook University（詹姆斯·库克大学）；Queensland University of Technology（昆士兰理工大学）
When approaching a clustering problem, choosing the right clustering algorithm and parameters is essential, as each clustering algorithm is proficient at finding clusters of a particular nature. Due to the unsupervised nature of clustering algorithms, there are no ground truth values available for empirical evaluation, which makes automation of the parameter selection process through hyperparameter tuning difficult. Previous approaches to hyperparameter tuning for clustering algorithms have relied on internal metrics, which are often biased towards certain algorithms, or having some ground tru…
University of Toronto（多伦多大学）；Vector Institute（向量学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such as the curvature can help de-sensitize common hyperparameters. Based on this intuition, we explore the use of exact per-sample Hessian-vector products and gradients to construct optimizers that are self-tuning and hyperparameter-free. Based on a dynamics model of the gradient, we derive a process which leads to a curvature-corrected, noise-adaptive online gradient estimate. The smoothness of our updates makes it mor…
Clova AI Research, NAVER Corp.（NAVER公司Clova人工智能研究院）；Ulsan National Institute of Science and Technology（蔚山国立科学技术院）
Many hyperparameter optimization (HyperOpt) methods assume restricted computing resources and mainly focus on enhancing performance. Here we propose a novel cloud-based HyperOpt (CHOPT) framework which can efficiently utilize shared computing resources while supporting various HyperOpt algorithms. We incorporate convenient web-based user interfaces, visualization, and analysis tools, enabling users to easily control optimization procedures and build up valuable insights with an iterative analysis procedure. Furthermore, our framework can be incorporated with any cloud platform, thus complement…
Ostfalia University of Applied Sciences（东法利亚应用科学大学）；Clausthal University of Technology（克劳斯塔尔工业大学）；Helmholtz Centre for Infection Research（亥姆霍兹感染研究中心）
Background: Embedded feature selection in high-dimensional data with very small sample sizes requires optimized hyperparameters for the model building process. For this hyperparameter optimization, nested cross-validation must be applied to avoid a biased performance estimation. The resulting repeated training with high-dimensional data leads to very long computation times. Moreover, it is likely to observe a high variance in the individual performance evaluation metrics caused by outliers in tiny validation sets. Therefore, early stopping applying standard pruning algorithms to save time risk…
Univ Lyon（里昂大学）；ENS de Lyon（里昂高等师范学院）；Univ Lyon 1（里昂第一大学）；CNRS（法国国家科学研究中心）；Université de Bourgogne Franche-Comté（勃艮第-弗朗什-孔泰大学）
Penalized Least Squares are widely used in signal and image processing. Yet, it suffers from a major limitation since it requires fine-tuning of the regularization parameters. Under assumptions on the noise probability distribution, Stein-based approaches provide unbiased estimator of the quadratic risk. The Generalized Stein Unbiased Risk Estimator is revisited to handle correlated Gaussian noise without requiring to invert the covariance matrix. Then, in order to avoid expansive grid search, it is necessary to design algorithmic scheme minimizing the quadratic risk with respect to regulariza…
Novel technologies in automated machine learning ease the complexity of algorithm selection and hyperparameter optimization. Hyperparameters are important for machine learning models as they significantly influence the performance of machine learning models. Many optimization techniques have achieved notable success in hyperparameter tuning and surpassed the performance of human experts. However, depending on such techniques as blackbox algorithms can leave machine learning practitioners without insight into the relative importance of different hyperparameters. In this paper, we consider build…
