As Transformer-based models have achieved impressive performance on various time series tasks, Long-Term Series Forecasting (LTSF) tasks have also received extensive attention in recent years. However, due to the inherent computational complexity and long sequences demanding of Transformer-based methods, its application on LTSF tasks still has two major issues that need to be further investigated: 1) Whether the sparse attention mechanism designed by these methods actually reduce the running time on real devices; 2) Whether these models need extra long input sequences to guarantee their performance? The answers given in this paper are negative. Therefore, to better copy with these two issues, we design a lightweight Period-Attention mechanism (Periodformer), which renovates the aggregation of long-term subseries via explicit periodicity and short-term subseries via built-in proximity. Meanwhile, a gating mechanism is embedded into Periodformer to regulate the influence of the attention module on the prediction results. Furthermore, to take full advantage of GPUs for fast hyperparameter optimization (e.g., finding the suitable input length), a Multi-GPU Asynchronous parallel algorithm based on Bayesian Optimization (MABO) is presented. MABO allocates a process to each GPU via a queue mechanism, and then creates multiple trials at a time for asynchronous parallel search, which greatly reduces the search time. Compared with the state-of-the-art methods, the prediction error of Periodformer reduced by 13% and 26% for multivariate and univariate forecasting, respectively. In addition, MABO reduces the average search time by 46% while finding better hyperparameters. As a conclusion, this paper indicates that LTSF may not need complex attention and extra long input sequences. The code has been open sourced on Github.
Minimizing response times is crucial for emergency medical services to reduce patients' waiting times and to increase their survival rates. Many models exist to optimize operational tasks such as ambulance allocation and dispatching. Including accurate demand forecasts in such models can improve operational decision-making. Against this background, we present a novel convolutional neural network (CNN) architecture that transforms time series data into heatmaps to predict ambulance demand. Applying such predictions requires incorporating external features that influence ambulance demands. We contribute to the existing literature by providing a flexible, generic CNN architecture, allowing for the inclusion of external features with varying dimensions. Additionally, we provide a feature selection and hyperparameter optimization framework utilizing Bayesian optimization. We integrate historical ambulance demand and external information such as weather, events, holidays, and time. To show the superiority of the developed CNN architecture over existing approaches, we conduct a case study for Seattle's 911 call data and include external information. We show that the developed CNN architecture outperforms existing state-of-the-art methods and industry practice by more than 9%.
Sampling techniques are used in many fields, including design of experiments, image processing, and graphics. The techniques in each field are designed to meet the constraints specific to that field such as uniform coverage of the range of each dimension or random samples that are at least a certain distance apart from each other. When an application imposes new constraints, for example, by requiring samples in a non-rectangular domain or the addition of new samples to an existing set, a common solution is to modify the algorithm currently in use, often with less than satisfactory results. As an alternative, we propose the concept of intelligent sampling, where we devise algorithms specifically tailored to meet our sampling needs, either by creating new algorithms or by modifying suitable algorithms from other fields. Surprisingly, both qualitative and quantitative comparisons indicate that some relatively simple algorithms can be easily modified to meet the many sampling requirements of surrogate modeling, hyperparameter optimization, and data analysis; these algorithms outperform their more sophisticated counterparts currently in use, resulting in better use of time and computer resources.
Approximate inference in Gaussian process (GP) models with non-conjugate likelihoods gets entangled with the learning of the model hyperparameters. We improve hyperparameter learning in GP models and focus on the interplay between variational inference (VI) and the learning target. While VI's lower bound to the marginal likelihood is a suitable objective for inferring the approximate posterior, we show that a direct approximation of the marginal likelihood as in Expectation Propagation (EP) is a better learning objective for hyperparameter optimization. We design a hybrid training procedure to bring the best of both worlds: it leverages conjugate-computation VI for inference and uses an EP-like marginal likelihood approximation for hyperparameter learning. We compare VI, EP, Laplace approximation, and our proposed training procedure and empirically demonstrate the effectiveness of our proposal across a wide range of data sets.
Selecting hyperparameters in deep learning greatly impacts its effectiveness but requires manual effort and expertise. Recent works show that Bayesian model selection with Laplace approximations can allow to optimize such hyperparameters just like standard neural network parameters using gradients and on the training data. However, estimating a single hyperparameter gradient requires a pass through the entire dataset, limiting the scalability of such algorithms. In this work, we overcome this issue by introducing lower bounds to the linearized Laplace approximation of the marginal likelihood. In contrast to previous estimators, these bounds are amenable to stochastic-gradient-based optimization and allow to trade off estimation accuracy against computational complexity. We derive them using the function-space form of the linearized Laplace, which can be estimated using the neural tangent kernel. Experimentally, we show that the estimators can significantly accelerate gradient-based hyperparameter optimization.
With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly searches for the optimal pretrained model and the hyperparameters for finetuning it. Our method transfers knowledge about the performance of many pretrained models with multiple hyperparameter configurations on a series of datasets. To this aim, we evaluated over 20k hyperparameter configurations for finetuning 24 pretrained image classification models on 87 datasets to generate a large-scale meta-dataset. We meta-learn a multi-fidelity performance predictor on the learning curves of this meta-dataset and use it for fast hyperparameter optimization on new datasets. We empirically demonstrate that our resulting approach can quickly select an accurate pretrained model for a new dataset together with its optimal hyperparameters.
Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for the considered bilevel problems, which generalizes the existing metric, for a nonconvex lower-level objective that satisfies the Polyak-{\L}ojasiewicz (PL) condition. We then propose a Generalized ALternating mEthod for bilevel opTimization (GALET) tailored to BLO with convex PL LL problem and establish that GALET achieves an $\epsilon$-stationary point for the considered problem within $\tilde{\cal O}(\epsilon^{-1})$ iterations, which matches the iteration complexity of GD for single-level smooth nonconvex problems.
Population Based Training (PBT) is an efficient hyperparameter optimization algorithm. PBT is a single-objective algorithm, but many real-world hyperparameter optimization problems involve two or more conflicting objectives. In this work, we therefore introduce a multi-objective version of PBT, MO-PBT. Our experiments on diverse multi-objective hyperparameter optimization problems (Precision/Recall, Accuracy/Fairness, Accuracy/Adversarial Robustness) show that MO-PBT outperforms random search, single-objective PBT, and the state-of-the-art multi-objective hyperparameter optimization algorithm MO-ASHA.
In order to improve reproducibility, deep reinforcement learning (RL) has been adopting better scientific practices such as standardized evaluation metrics and reporting. However, the process of hyperparameter optimization still varies widely across papers, which makes it challenging to compare RL algorithms fairly. In this paper, we show that hyperparameter choices in RL can significantly affect the agent's final performance and sample efficiency, and that the hyperparameter landscape can strongly depend on the tuning seed which may lead to overfitting. We therefore propose adopting established best practices from AutoML, such as the separation of tuning and testing seeds, as well as principled hyperparameter optimization (HPO) across a broad search space. We support this by comparing multiple state-of-the-art HPO tools on a range of RL algorithms and environments to their hand-tuned counterparts, demonstrating that HPO approaches often have higher performance and lower compute overhead. As a result of our findings, we recommend a set of best practices for the RL community, which should result in stronger empirical results with fewer computational costs, better reproducibility, and thus faster progress. In order to encourage the adoption of these practices, we provide plug-and-play implementations of the tuning algorithms used in this paper at https://github.com/facebookresearch/how-to-autorl.
This work provides a solution to the challenge of small amounts of training data in Non-Destructive Ultrasonic Testing for composite components. It was demonstrated that direct simulation alone is ineffective at producing training data that was representative of the experimental domain due to poor noise reconstruction. Therefore, four unique synthetic data generation methods were proposed which use semi-analytical simulated data as a foundation. Each method was evaluated on its classification performance of real experimental images when trained on a Convolutional Neural Network which underwent hyperparameter optimization using a genetic algorithm. The first method introduced task specific modifications to CycleGAN, to learn the mapping from physics-based simulations of defect indications to experimental indications in resulting ultrasound images. The second method was based on combining real experimental defect free images with simulated defect responses. The final two methods fully simulated the noise responses at an image and signal level respectively. The purely simulated data produced a mean classification F1 score of 0.394. However, when trained on the new synthetic datasets, a significant improvement in classification performance on experimental data was realized, with mean classification F1 scores of 0.843, 0.688, 0.629, and 0.738 for the respective approaches.
Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. The mainstream learning-based methods mainly acquire the enhanced model by learning the data distribution from the specific scenes, causing poor adaptability (even failure) when meeting real-world scenarios that have never been encountered before. The main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes. To remedy this, we first explore relationships between diverse low-light scenes based on statistical analysis, i.e., the network parameters of the encoder trained in different data distributions are close. We introduce the bilevel paradigm to model the above latent correspondence from the perspective of hyperparameter optimization. A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes (i.e., freezing the encoder in the adaptation and testing phases). Further, we define a reinforced bilevel learning framework to provide a meta-initialization for scene-specific decoder to further ameliorate visual quality. Moreover, to improve the practicability, we establish a Retinex-induced architecture with adaptive denoising and apply our built learning framework to acquire its parameters by using two training losses including supervised and unsupervised forms. Extensive experimental evaluations on multiple datasets verify our adaptability and competitive performance against existing state-of-the-art works. The code and datasets will be available at https://github.com/vis-opt-group/BL.
Recent work has highlighted the complex influence training hyperparameters, e.g., the number of training epochs, can have on the prunability of machine learning models. Perhaps surprisingly, a systematic approach to predict precisely how adjusting a specific hyperparameter will affect prunability remains elusive. To address this gap, we introduce a phenomenological model grounded in the statistical mechanics of learning. Our approach uses temperature-like and load-like parameters to model the impact of neural network (NN) training hyperparameters on pruning performance. A key empirical result we identify is a sharp transition phenomenon: depending on the value of a load-like parameter in the pruned model, increasing the value of a temperature-like parameter in the pre-pruned model may either enhance or impair subsequent pruning performance. Based on this transition, we build a three-regime model by taxonomizing the global structure of the pruned NN loss landscape. Our model reveals that the dichotomous effect of high temperature is associated with transitions between distinct types of global structures in the post-pruned model. Based on our results, we present three case-studies: 1) determining whether to increase or decrease a hyperparameter for improved pruning; 2) selecting the best model to prune from a family of models; and 3) tuning the hyperparameter of the Sharpness Aware Minimization method for better pruning performance.
In this work, we propose a hyperparameter optimization method named \emph{HyperTime} to find hyperparameters robust to potential temporal distribution shifts in the unseen test data. Our work is motivated by an important observation that it is, in many cases, possible to achieve temporally robust predictive performance via hyperparameter optimization. Based on this observation, we leverage the `worst-case-oriented' philosophy from the robust optimization literature to help find such robust hyperparameter configurations. HyperTime imposes a lexicographic priority order on average validation loss and worst-case validation loss over chronological validation sets. We perform a theoretical analysis on the upper bound of the expected test loss, which reveals the unique advantages of our approach. We also demonstrate the strong empirical performance of the proposed method on multiple machine learning tasks with temporal distribution shifts.
In this paper, we use Prior-data Fitted Networks (PFNs) as a flexible surrogate for Bayesian Optimization (BO). PFNs are neural processes that are trained to approximate the posterior predictive distribution (PPD) through in-context learning on any prior distribution that can be efficiently sampled from. We describe how this flexibility can be exploited for surrogate modeling in BO. We use PFNs to mimic a naive Gaussian process (GP), an advanced GP, and a Bayesian Neural Network (BNN). In addition, we show how to incorporate further information into the prior, such as allowing hints about the position of optima (user priors), ignoring irrelevant dimensions, and performing non-myopic BO by learning the acquisition function. The flexibility underlying these extensions opens up vast possibilities for using PFNs for BO. We demonstrate the usefulness of PFNs for BO in a large-scale evaluation on artificial GP samples and three different hyperparameter optimization testbeds: HPO-B, Bayesmark, and PD1. We publish code alongside trained models at github.com/automl/PFNs4BO.
This work explores the use of gradient boosting in the context of classification. Four popular implementations, including original GBM algorithm and selected state-of-the-art gradient boosting frameworks (i.e. XGBoost, LightGBM and CatBoost), have been thoroughly compared on several publicly available real-world datasets of sufficient diversity. In the study, special emphasis was placed on hyperparameter optimization, specifically comparing two tuning strategies, i.e. randomized search and Bayesian optimization using the Tree-stuctured Parzen Estimator. The performance of considered methods was investigated in terms of common classification accuracy metrics as well as runtime and tuning time. Additionally, obtained results have been validated using appropriate statistical testing. An attempt was made to indicate a gradient boosting variant showing the right balance between effectiveness, reliability and ease of use.
Automated Machine Learning (AutoML) is a promising direction for democratizing AI by automatically deploying Machine Learning systems with minimal human expertise. The core technical challenge behind AutoML is optimizing the pipelines of Machine Learning systems (e.g. the choice of preprocessing, augmentations, models, optimizers, etc.). Existing Pipeline Optimization techniques fail to explore deep interactions between pipeline stages/components. As a remedy, this paper proposes a novel neural architecture that captures the deep interaction between the components of a Machine Learning pipeline. We propose embedding pipelines into a latent representation through a novel per-component encoder mechanism. To search for optimal pipelines, such pipeline embeddings are used within deep-kernel Gaussian Process surrogates inside a Bayesian Optimization setup. Furthermore, we meta-learn the parameters of the pipeline embedding network using existing evaluations of pipelines on diverse collections of related datasets (a.k.a. meta-datasets). Through extensive experiments on three large-scale meta-datasets, we demonstrate that pipeline embeddings yield state-of-the-art results in Pipeline Optimization.
Deploying deep neural networks (DNNs) on microcontrollers (TinyML) is a common trend to process the increasing amount of sensor data generated at the edge, but in practice, resource and latency constraints make it difficult to find optimal DNN candidates. Neural architecture search (NAS) is an excellent approach to automate this search and can easily be combined with DNN compression techniques commonly used in TinyML. However, many NAS techniques are not only computationally expensive, especially hyperparameter optimization (HPO), but also often focus on optimizing only a single objective, e.g., maximizing accuracy, without considering additional objectives such as memory requirements or computational complexity of a DNN, which are key to making deployment at the edge feasible. In this paper, we propose a novel NAS strategy for TinyML based on multi-objective Bayesian optimization (MOBOpt) and an ensemble of competing parametric policies trained using Augmented Random Search (ARS) reinforcement learning (RL) agents. Our methodology aims at efficiently finding tradeoffs between a DNN's predictive accuracy, memory requirements on a given target system, and computational complexity. Our experiments show that we consistently outperform existing MOBOpt approaches on different datasets and architectures such as ResNet-18 and MobileNetV3.
Searching for potential active compounds in large databases is a necessary step to reduce time and costs in modern drug discovery pipelines. Such virtual screening methods seek to provide predictions that allow the search space to be narrowed down. Although cheminformatics has made great progress in exploiting the potential of available big data, caution is needed to avoid introducing bias and provide useful predictions with new compounds. In this work, we propose the decision-support tool ALMERIA (Advanced Ligand Multiconformational Exploration with Robust Interpretable Artificial Intelligence) for estimating compound similarities and activity prediction based on pairwise molecular contrasts while considering their conformation variability. The methodology covers the entire pipeline from data preparation to model selection and hyperparameter optimization. It has been implemented using scalable software and methods to exploit large volumes of data -- in the order of several terabytes -- , offering a very quick response even for a large batch of queries. The implementation and experiments have been performed in a distributed computer cluster using a benchmark, the public access DUD-E database. In addition to cross-validation, detailed data split criteria have been used to evaluate the models on different data partitions to assess their true generalization ability with new compounds. Experiments show state-of-the-art performance for molecular activity prediction (ROC AUC: $0.99$, $0.96$, $0.87$), proving that the chosen data representation and modeling have good properties to generalize. Molecular conformations -- prediction performance and sensitivity analysis -- have also been evaluated. Finally, an interpretability analysis has been performed using the SHAP method.
The goal of hyperparameter tuning (or hyperparameter optimization) is to optimize the hyperparameters to improve the performance of the machine or deep learning model. spotPython (``Sequential Parameter Optimization Toolbox in Python'') is the Python version of the well-known hyperparameter tuner SPOT, which has been developed in the R programming environment for statistical analysis for over a decade. PyTorch is an optimized tensor library for deep learning using GPUs and CPUs. This document shows how to integrate the spotPython hyperparameter tuner into the PyTorch training workflow. As an example, the results of the CIFAR10 image classifier are used. In addition to an introduction to spotPython, this tutorial also includes a brief comparison with Ray Tune, a Python library for running experiments and tuning hyperparameters. This comparison is based on the PyTorch hyperparameter tuning tutorial. The advantages and disadvantages of both approaches are discussed. We show that spotPython achieves similar or even better results while being more flexible and transparent than Ray Tune.
Random Search is one of the most widely-used method for Hyperparameter Optimization, and is critical to the success of deep learning models. Despite its astonishing performance, little non-heuristic theory has been developed to describe the underlying working mechanism. This paper gives a theoretical accounting of Random Search. We introduce the concept of \emph{scattering dimension} that describes the landscape of the underlying function, and quantifies the performance of random search. We show that, when the environment is noise-free, the output of random search converges to the optimal value in probability at rate $ \widetilde{\mathcal{O}} \left( \left( \frac{1}{T} \right)^{ \frac{1}{d_s} } \right) $, where $ d_s \ge 0 $ is the scattering dimension of the underlying function. When the observed function values are corrupted by bounded $iid$ noise, the output of random search converges to the optimal value in probability at rate $ \widetilde{\mathcal{O}} \left( \left( \frac{1}{T} \right)^{ \frac{1}{d_s + 1} } \right) $. In addition, based on the principles of random search, we introduce an algorithm, called BLiN-MOS, for Lipschitz bandits in doubling metric spaces that are also endowed with a probability measure, and show that under mild conditions, BLiN-MOS achieves a regret rate of order $ \widetilde{\mathcal{O}} \left( T^{ \frac{d_z}{d_z + 1} } \right) $, where $d_z$ is the zooming dimension of the problem instance.