Several novel frameworks for hyperparameter search have emerged in the last decade, but most rely on strict, often normal, distributional assumptions, limiting search model flexibility. This paper proposes a novel optimization framework based on upper confidence bound sampling of conformal confidence intervals, whose weaker assumption of exchangeability enables greater choice of search model architectures. Several such architectures were explored and benchmarked on hyperparameter search of random forests and convolutional neural networks, displaying satisfactory interval coverage and superior tuning performance to random search.
Gradient-based multilevel optimization (MLO) has gained attention as a framework for studying numerous problems, ranging from hyperparameter optimization and meta-learning to neural architecture search and reinforcement learning. However, gradients in MLO, which are obtained by composing best-response Jacobians via the chain rule, are notoriously difficult to implement and memory/compute intensive. We take an initial step towards closing this gap by introducing Betty, a software library for large-scale MLO. At its core, we devise a novel dataflow graph for MLO, which allows us to (1) develop efficient automatic differentiation for MLO that reduces the computational complexity from O(d^3) to O(d^2), (2) incorporate systems support such as mixed-precision and data-parallel training for scalability, and (3) facilitate implementation of MLO programs of arbitrary complexity while allowing a modular interface for diverse algorithmic and systems design choices. We empirically demonstrate that Betty can be used to implement an array of MLO programs, while also observing up to 11% increase in test accuracy, 14% decrease in GPU memory usage, and 20% decrease in training wall time over existing implementations on multiple benchmarks. We also showcase that Betty enables scaling MLO to models with hundreds of millions of parameters. We open-source the code at https://github.com/leopard-ai/betty.
In this paper we consider the machine learning (ML) task of predicting tipping point transitions and long-term post-tipping-point behavior associated with the time evolution of an unknown (or partially unknown), non-stationary, potentially noisy and chaotic, dynamical system. We focus on the particularly challenging situation where the past dynamical state time series that is available for ML training predominantly lies in a restricted region of the state space, while the behavior to be predicted evolves on a larger state space set not fully observed by the ML model during training. In this situation, it is required that the ML prediction system have the ability to extrapolate to different dynamics past that which is observed during training. We investigate the extent to which ML methods are capable of accomplishing useful results for this task, as well as conditions under which they fail. In general, we found that the ML methods were surprisingly effective even in situations that were extremely challenging, but do (as one would expect) fail when ``too much" extrapolation is required. For the latter case, we investigate the effectiveness of combining the ML approach with conventional modeling based on scientific knowledge, thus forming a hybrid prediction system which we find can enable useful prediction even when its ML-based and knowledge-based components fail when acting alone. We also found that achieving useful results may require using very carefully selected ML hyperparameters and we propose a hyperparameter optimization strategy to address this problem. The main conclusion of this paper is that ML-based approaches are promising tools for predicting the behavior of non-stationary dynamical systems even in the case where the future evolution (perhaps due to the crossing of a tipping point) includes dynamics on a set outside of that explored by the training data.
Bayesian optimization (BO) is a promising approach for hyperparameter optimization of deep neural networks (DNNs), where each model training can take minutes to hours. In BO, a computationally cheap surrogate model is employed to learn the relationship between parameter configurations and their performance such as accuracy. Parallel BO methods often adopt single manager/multiple workers strategies to evaluate multiple hyperparameter configurations simultaneously. Despite significant hyperparameter evaluation time, the overhead in such centralized schemes prevents these methods to scale on a large number of workers. We present an asynchronous-decentralized BO, wherein each worker runs a sequential BO and asynchronously communicates its results through shared storage. We scale our method without loss of computational efficiency with above 95% of worker's utilization to 1,920 parallel workers (full production queue of the Polaris supercomputer) and demonstrate improvement in model accuracy as well as faster convergence on the CANDLE benchmark from the Exascale computing project.
The transfer fees of sports players have become astronomical. This is because bringing players of great future value to the club is essential for their survival. We present a case study on the key factors affecting the world's top soccer players' transfer fees based on the FIFA data analysis. To predict each player's market value, we propose an improved LightGBM model by optimizing its hyperparameter using a Tree-structured Parzen Estimator (TPE) algorithm. We identify prominent features by the SHapley Additive exPlanations (SHAP) algorithm. The proposed method has been compared against the baseline regression models (e.g., linear regression, lasso, elastic net, kernel ridge regression) and gradient boosting model without hyperparameter optimization. The optimized LightGBM model showed an excellent accuracy of approximately 3.8, 1.4, and 1.8 times on average compared to the regression baseline models, GBDT, and LightGBM model in terms of RMSE. Our model offers interpretability in deciding what attributes football clubs should consider in recruiting players in the future.
The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training. Many methods for hyperparameter optimization (HPO) of iterative learners, including DNNs, attempt to solve this problem by querying and learning a response surface while searching for the optimum of that surface. However, many of these methods make myopic queries, do not consider prior knowledge about the response structure, and/or perform a biased cost-aware search, all of which exacerbate identifying the best-performing model when a total cost budget is specified. This paper proposes a novel approach referred to as {\bf B}udget-{\bf A}ware {\bf P}lanning for {\bf I}terative Learners (BAPI) to solve HPO problems under a constrained cost budget. BAPI is an efficient non-myopic Bayesian optimization solution that accounts for the budget and leverages the prior knowledge about the objective function and cost function to select better configurations and to take more informed decisions during the evaluation (training). Experiments on diverse HPO benchmarks for iterative learners show that BAPI performs better than state-of-the-art baselines in most cases.
Machine learning (ML) offers powerful methods for detecting and modeling associations often in data with large feature spaces and complex associations. Many useful tools/packages (e.g. scikit-learn) have been developed to make the various elements of data handling, processing, modeling, and interpretation accessible. However, it is not trivial for most investigators to assemble these elements into a rigorous, replicatable, unbiased, and effective data analysis pipeline. Automated machine learning (AutoML) seeks to address these issues by simplifying the process of ML analysis for all. Here, we introduce STREAMLINE, a simple, transparent, end-to-end AutoML pipeline designed as a framework to easily conduct rigorous ML modeling and analysis (limited initially to binary classification). STREAMLINE is specifically designed to compare performance between datasets, ML algorithms, and other AutoML tools. It is unique among other autoML tools by offering a fully transparent and consistent baseline of comparison using a carefully designed series of pipeline elements including: (1) exploratory analysis, (2) basic data cleaning, (3) cross validation partitioning, (4) data scaling and imputation, (5) filter-based feature importance estimation, (6) collective feature selection, (7) ML modeling with `Optuna' hyperparameter optimization across 15 established algorithms (including less well-known Genetic Programming and rule-based ML), (8) evaluation across 16 classification metrics, (9) model feature importance estimation, (10) statistical significance comparisons, and (11) automatically exporting all results, plots, a PDF summary report, and models that can be easily applied to replication data.
Deep neural architectures have profound impact on achieved performance in many of today's AI tasks, yet, their design still heavily relies on human prior knowledge and experience. Neural architecture search (NAS) together with hyperparameter optimization (HO) helps to reduce this dependence. However, state of the art NAS and HO rapidly become infeasible with increasing amount of data being stored in a distributed fashion, typically violating data privacy regulations such as GDPR and CCPA. As a remedy, we introduce FEATHERS - $\textbf{FE}$derated $\textbf{A}$rchi$\textbf{T}$ecture and $\textbf{H}$yp$\textbf{ER}$parameter $\textbf{S}$earch, a method that not only optimizes both neural architectures and optimization-related hyperparameters jointly in distributed data settings, but further adheres to data privacy through the use of differential privacy (DP). We show that FEATHERS efficiently optimizes architectural and optimization-related hyperparameters alike, while demonstrating convergence on classification tasks at no detriment to model performance when complying with privacy constraints.
Optimal control problems naturally arise in many scientific applications where one wishes to steer a dynamical system from a certain initial state $\mathbf{x}_0$ to a desired target state $\mathbf{x}^*$ in finite time $T$. Recent advances in deep learning and neural network-based optimization have contributed to the development of methods that can help solve control problems involving high-dimensional dynamical systems. In particular, the framework of neural ordinary differential equations (neural ODEs) provides an efficient means to iteratively approximate continuous time control functions associated with analytically intractable and computationally demanding control tasks. Although neural ODE controllers have shown great potential in solving complex control problems, the understanding of the effects of hyperparameters such as network structure and optimizers on learning performance is still very limited. Our work aims at addressing some of these knowledge gaps to conduct efficient hyperparameter optimization. To this end, we first analyze how truncated and non-truncated backpropagation through time affect runtime performance and the ability of neural networks to learn optimal control functions. Using analytical and numerical methods, we then study the role of parameter initializations, optimizers, and neural-network architecture. Finally, we connect our results to the ability of neural ODE controllers to implicitly regularize control energy.
Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional metrics or constraints must be considered when determining an optimal configuration, resulting in a multi-objective optimization problem. This is often neglected in practice, due to a lack of knowledge and readily available software implementations for multi-objective hyperparameter optimization. In this work, we introduce the reader to the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. Furthermore, we provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.
We introduce DiffOpt.jl, a Julia library to differentiate through the solution of optimization problems with respect to arbitrary parameters present in the objective and/or constraints. The library builds upon MathOptInterface, thus leveraging the rich ecosystem of solvers and composing well with modeling languages like JuMP. DiffOpt offers both forward and reverse differentiation modes, enabling multiple use cases from hyperparameter optimization to backpropagation and sensitivity analysis, bridging constrained optimization with end-to-end differentiable programming. DiffOpt is built on two known rules for differentiating quadratic programming and conic programming standard forms. However, thanks ability to differentiate through model transformation, the user is not limited to these forms and can differentiate with respect to the parameters of any model that can be reformulated into these standard forms. This notably includes programs mixing affine conic constraints and convex quadratic constraints or objective function.
Despite all the benefits of automated hyperparameter optimization (HPO), most modern HPO algorithms are black-boxes themselves. This makes it difficult to understand the decision process which leads to the selected configuration, reduces trust in HPO, and thus hinders its broad adoption. Here, we study the combination of HPO with interpretable machine learning (IML) methods such as partial dependence plots. These techniques are more and more used to explain the marginal effect of hyperparameters on the black-box cost function or to quantify the importance of hyperparameters. However, if such methods are naively applied to the experimental data of the HPO process in a post-hoc manner, the underlying sampling bias of the optimizer can distort interpretations. We propose a modified HPO method which efficiently balances the search for the global optimum w.r.t. predictive performance \emph{and} the reliable estimation of IML explanations of an underlying black-box function by coupling Bayesian optimization and Bayesian Algorithm Execution. On benchmark cases of both synthetic objectives and HPO of a neural network, we demonstrate that our method returns more reliable explanations of the underlying black-box without a loss of optimization performance.
Online travel agencies (OTA's) advertise their website offers on meta-search bidding engines. The problem of predicting the number of clicks a hotel would receive for a given bid amount is an important step in the management of an OTA's advertisement campaign on a meta-search engine, because bid times number of clicks defines the cost to be generated. Various regressors are ensembled in this work to improve click prediction performance. Following the preprocessing procedures, the feature set is divided into train and test groups depending on the logging date of the samples. The data collection is then subjected to feature elimination via utilizing XGBoost, which significantly reduces the dimension of features. The optimum hyper-parameters are then found by applying Bayesian hyperparameter optimization to XGBoost, LightGBM, and SGD models. The different trained models are tested separately as well as combined to form ensemble models. Four alternative ensemble solutions have been suggested. The same test set is used to test both individual and ensemble models, and the results of 46 model combinations demonstrate that stack ensemble models yield the desired R2 score of all. In conclusion, the ensemble model improves the prediction performance by about 10%.
Hyperparameter optimization (HPO) is crucial for machine learning algorithms to achieve satisfactory performance, whose progress has been boosted by related benchmarks. Nonetheless, existing efforts in benchmarking all focus on HPO for traditional centralized learning while ignoring federated learning (FL), a promising paradigm for collaboratively learning models from dispersed data. In this paper, we first identify some uniqueness of HPO for FL algorithms from various aspects. Due to this uniqueness, existing HPO benchmarks no longer satisfy the need to compare HPO methods in the FL setting. To facilitate the research of HPO in the FL setting, we propose and implement a benchmark suite FedHPO-B that incorporates comprehensive FL tasks, enables efficient function evaluations, and eases continuing extensions. We also conduct extensive experiments based on FedHPO-B to benchmark a few HPO methods. We open-source FedHPO-B at https://github.com/alibaba/FederatedScope/tree/master/benchmark/FedHPOB.
With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important. Motivated by the tuning behaviors of human experts, it is intuitive to leverage auxiliary knowledge from past HPO tasks to accelerate the current HPO task. In this paper, we propose TransBO, a novel two-phase transfer learning framework for HPO, which can deal with the complementary nature among source tasks and dynamics during knowledge aggregation issues simultaneously. This framework extracts and aggregates source and target knowledge jointly and adaptively, where the weights can be learned in a principled manner. The extensive experiments, including static and dynamic transfer learning settings and neural architecture search, demonstrate the superiority of TransBO over the state-of-the-arts.
We present a novel approach to estimating physical properties of objects from video. Our approach consists of a physics engine and a correction estimator. Starting from the initial observed state, object behavior is simulated forward in time. Based on the simulated and observed behavior, the correction estimator then determines refined physical parameters for each object. The method can be iterated for increased precision. Our approach is generic, as it allows for the use of an arbitrary - not necessarily differentiable - physics engine and correction estimator. For the latter, we evaluate both gradient-free hyperparameter optimization and a deep convolutional neural network. We demonstrate faster and more robust convergence of the learned method in several simulated 2D scenarios focusing on bin situations.
Physics-informed neural networks (PINNs) are revolutionizing science and engineering practice by bringing together the power of deep learning to bear on scientific computation. In forward modeling problems, PINNs are meshless partial differential equation (PDE) solvers that can handle irregular, high-dimensional physical domains. Naturally, the neural architecture hyperparameters have a large impact on the efficiency and accuracy of the PINN solver. However, this remains an open and challenging problem because of the large search space and the difficulty of identifying a proper search objective for PDEs. Here, we propose Auto-PINN, the first systematic, automated hyperparameter optimization approach for PINNs, which employs Neural Architecture Search (NAS) techniques to PINN design. Auto-PINN avoids manually or exhaustively searching the hyperparameter space associated with PINNs. A comprehensive set of pre-experiments using standard PDE benchmarks allows us to probe the structure-performance relationship in PINNs. We find that the different hyperparameters can be decoupled, and that the training loss function of PINNs is a good search objective. Comparison experiments with baseline methods demonstrate that Auto-PINN produces neural architectures with superior stability and accuracy over alternative baselines.
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 largest HPO datasets. Our extensive experiments demonstrate that the OptFormer can simultaneously imitate at least 7 different HPO algorithms, which can be further improved via its function uncertainty estimates. Compared to a Gaussian Process, the OptFormer also learns a robust prior distribution for hyperparameter response functions, and can thereby provide more accurate and better calibrated predictions. This work paves the path to future extensions for training a Transformer-based model as a general HPO optimizer.
Deploying deep neural networks (DNNs) on IoT and mobile devices is a challenging task due to their limited computational resources. Thus, demanding tasks are often entirely offloaded to edge servers which can accelerate inference, however, it also causes communication cost and evokes privacy concerns. In addition, this approach leaves the computational capacity of end devices unused. Split computing is a paradigm where a DNN is split into two sections; the first section is executed on the end device, and the output is transmitted to the edge server where the final section is executed. Here, we introduce dynamic split computing, where the optimal split location is dynamically selected based on the state of the communication channel. By using natural bottlenecks that already exist in modern DNN architectures, dynamic split computing avoids retraining and hyperparameter optimization, and does not have any negative impact on the final accuracy of DNNs. Through extensive experiments, we show that dynamic split computing achieves faster inference in edge computing environments where the data rate and server load vary over time.
Deep Learning (DL) is a surprisingly successful branch of machine learning. The success of DL is usually explained by focusing analysis on a particular recent algorithm and its traits. Instead, we propose that an explanation of the success of DL must look at the population of all algorithms in the field and how they have evolved over time. We argue that cultural evolution is a useful framework to explain the success of DL. In analogy to biology, we use `development' to mean the process converting the pseudocode or text description of an algorithm into a fully trained model. This includes writing the programming code, compiling and running the program, and training the model. If all parts of the process don't align well then the resultant model will be useless (if the code runs at all!). This is a constraint. A core component of evolutionary developmental biology is the concept of deconstraints -- these are modification to the developmental process that avoid complete failure by automatically accommodating changes in other components. We suggest that many important innovations in DL, from neural networks themselves to hyperparameter optimization and AutoGrad, can be seen as developmental deconstraints. These deconstraints can be very helpful to both the particular algorithm in how it handles challenges in implementation and the overall field of DL in how easy it is for new ideas to be generated. We highlight how our perspective can both advance DL and lead to new insights for evolutionary biology.