BayesianOptimization(BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function through a probabilistic surrogate model, including Tree-structured Parzen Estimator (TPE), random forest (SMAC), and Gaussian process (GP). However, few methods have been explored to estimate the relative rankings of candidates, which can be more robust to noise and have better practicality than absolute function responses, especially when the function responses are intractable but preferences can be acquired. To this end, we propose a novel ranking-based surrogate model based on the Poisson process and introduce an efficient BO framework, namely Poisson Process Bayesian Optimization (PoPBO). Two tailored acquisition functions are further derived from classic LCB and EI to accommodate it. Compared to the classic GP-BO method, our PoPBO has lower computation costs and better robustness to noise, which is verified by abundant experiments. The results on both simulated and real-world benchmarks, including hyperparameter optimization (HPO) and neural architecture search (NAS), show the effectiveness of PoPBO.
In Hyperparameter Optimization (HPO), only the hyperparameter configuration with the best performance is chosen after performing several trials, then, discarding the effort of training all the models with every hyperparameter configuration trial and performing an ensemble of all them. This ensemble consists of simply averaging the model predictions or weighting the models by a certain probability. Recently, other more sophisticated ensemble strategies, such as the Caruana method or the stacking strategy has been proposed. On the one hand, the Caruana method performs well in HPO ensemble, since it is not affected by the effects of multicollinearity, which is prevalent in HPO. It just computes the average over a subset of predictions with replacement. But it does not benefit from the generalization power of a learning process. On the other hand, stacking methods include a learning procedure since a meta-learner is required to perform the ensemble. Yet, one hardly finds advice about which meta-learner is adequate. Besides, some meta-learners may suffer from the effects of multicollinearity or need to be tuned to reduce them. This paper explores meta-learners for stacking ensemble in HPO, free of hyperparameter tuning, able to reduce the effects of multicollinearity and considering the ensemble learning process generalization power. At this respect, the boosting strategy seems promising as a stacking meta-learner. In fact, it completely removes the effects of multicollinearity. This paper also proposes an implicit regularization in the classical boosting method and a novel non-parametric stop criterion suitable only for boosting and specifically designed for HPO. The synergy between these two improvements over boosting exhibits competitive and promising predictive power performance compared to other existing meta-learners and ensemble approaches for HPO other than the stacking ensemble.
One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current RL algorithms exist, but there is a lack of a modular suite of tools combining different robotic simulators and platforms, data visualization, hyperparameter optimization, and baseline experiments. To address this problem, we present Scilab-RL, a software framework for efficient research in cognitive modeling and reinforcement learning for robotic agents. The framework focuses on goal-conditioned reinforcement learning using Stable Baselines 3 and the OpenAI gym interface. It enables native possibilities for experiment visualizations and hyperparameter optimization. We describe how these features enable researchers to conduct experiments with minimal time effort, thus maximizing research output.
Manual parameter tuning of cyber-physical systems is a common practice, but it is labor-intensive. Bayesian Optimization (BO) offers an automated alternative, yet its black-box nature reduces trust and limits human-BO collaborative system tuning. Experts struggle to interpret BO recommendations due to the lack of explanations. This paper addresses the post-hoc BO explainability problem for cyber-physical systems. We introduce TNTRules (Tune-No-Tune Rules), a novel algorithm that provides both global and local explanations for BO recommendations. TNTRules generates actionable rules and visual graphs, identifying optimal solution bounds and ranges, as well as potential alternative solutions. Unlike existing explainable AI (XAI) methods, TNTRules is tailored specifically for BO, by encoding uncertainty via a variance pruning technique and hierarchical agglomerative clustering. A multi-objective optimization approach allows maximizing explanation quality. We evaluate TNTRules using established XAI metrics (Correctness, Completeness, and Compactness) and compare it against adapted baseline methods. The results demonstrate that TNTRules generates high-fidelity, compact, and complete explanations, significantly outperforming three baselines on 5 multi-objective testing functions and 2 hyperparameter tuning problems.
Bilevel optimization is an important formulation for many machine learning problems. Current bilevel optimization algorithms assume that the gradient of the upper-level function is Lipschitz. However, recent studies reveal that certain neural networks such as recurrent neural networks (RNNs) and long-short-term memory networks (LSTMs) exhibit potential unbounded smoothness, rendering conventional bilevel optimization algorithms unsuitable. In this paper, we design a new bilevel optimization algorithm, namely BO-REP, to address this challenge. This algorithm updates the upper-level variable using normalized momentum and incorporates two novel techniques for updating the lower-level variable: \textit{initialization refinement} and \textit{periodic updates}. Specifically, once the upper-level variable is initialized, a subroutine is invoked to obtain a refined estimate of the corresponding optimal lower-level variable, and the lower-level variable is updated only after every specific period instead of each iteration. When the upper-level problem is nonconvex and unbounded smooth, and the lower-level problem is strongly convex, we prove that our algorithm requires $\widetilde{\mathcal{O}}(1/\epsilon^4)$ iterations to find an $\epsilon$-stationary point in the stochastic setting, where each iteration involves calling a stochastic gradient or Hessian-vector product oracle. Notably, this result matches the state-of-the-art complexity results under the bounded smoothness setting and without mean-squared smoothness of the stochastic gradient, up to logarithmic factors. Our proof relies on novel technical lemmas for the periodically updated lower-level variable, which are of independent interest. Our experiments on hyper-representation learning, hyperparameter optimization, and data hyper-cleaning for text classification tasks demonstrate the effectiveness of our proposed algorithm.
Fast changing states or volatile environments pose a significant challenge to online optimization, which needs to perform rapid adaptation under limited observation. In this paper, we give query and regret optimal bandit algorithms under the strict notion of strongly adaptive regret, which measures the maximum regret over any contiguous interval $I$. Due to its worst-case nature, there is an almost-linear $\Omega(|I|^{1-\epsilon})$ regret lower bound, when only one query per round is allowed [Daniely el al, ICML 2015]. Surprisingly, with just two queries per round, we give Strongly Adaptive Bandit Learner (StABL) that achieves $\tilde{O}(\sqrt{n|I|})$ adaptive regret for multi-armed bandits with $n$ arms. The bound is tight and cannot be improved in general. Our algorithm leverages a multiplicative update scheme of varying stepsizes and a carefully chosen observation distribution to control the variance. Furthermore, we extend our results and provide optimal algorithms in the bandit convex optimization setting. Finally, we empirically demonstrate the superior performance of our algorithms under volatile environments and for downstream tasks, such as algorithm selection for hyperparameter optimization.
The goal of this paper is to test three classes of neural network (NN) architectures based on four-dimensional (4D) hypercomplex algebras for time series prediction. We evaluate different architectures, varying the input layers to include convolutional, Long Short-Term Memory (LSTM), or dense hypercomplex layers for 4D algebras. Four related Stock Market time series are used as input data, with the prediction focused on one of them. Hyperparameter optimization for each architecture class was conducted to compare the best-performing neural networks within each class. The results indicate that, in most cases, architectures with hypercomplex dense layers achieve similar Mean Absolute Error (MAE) accuracy compared to other architectures, but with significantly fewer trainable parameters. Consequently, hypercomplex neural networks demonstrate the ability to learn and process time series data faster than the other tested architectures. Additionally, it was found that the ordering of the input time series have a notable impact on effectiveness.
This paper describes a machine learning method to automate reading of cockpit gauges, using a CNN to invert affine transformations and deduce aircraft states from instrument images. Validated with synthetic images of a turn-and-bank indicator, this research introduces methods such as generating datasets from a single image, the 'Clean Training Principle' for optimal noise-free training, and CNN interpolation for continuous value predictions from categorical data. It also offers insights into hyperparameter optimization and ML system software engineering.
Reservoir computing is a machine learning framework where the readouts from a nonlinear system (the reservoir) are trained so that the output from the reservoir, when forced with an input signal, reproduces a desired output signal. A common implementation of reservoir computers is to use a recurrent neural network as the reservoir. The design of this network can have significant effects on the performance of the reservoir computer. In this paper we study the effect of the node activation function on the ability of reservoir computers to learn and predict chaotic time series. We find that the Forecast Horizon (FH), the time during which the reservoir's predictions remain accurate, can vary by an order of magnitude across a set of 16 activation functions used in machine learning. By using different functions from this set, and by modifying their parameters, we explore whether the entropy of node activation levels or the curvature of the activation functions determine the predictive ability of the reservoirs. We find that the FH is low when the activation function is used in a region where it has low curvature, and a positive correlation between curvature and FH. For the activation functions studied we find that the largest FH generally occurs at intermediate levels of the entropy of node activation levels. Our results show that the performance of reservoir computers is very sensitive to the activation function shape. Therefore, modifying this shape in hyperparameter optimization algorithms can lead to improvements in reservoir computer performance.
Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach; 2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes $\mu$-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed $\mu$-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the $\mu$-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain $\epsilon$-stationary point is upper bounded by $\mathcal{O}(\frac{1}{\epsilon^2})$. Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80$\%$.
Survival Analysis (SA) constitutes the default method for time-to-event modeling due to its ability to estimate event probabilities of sparsely occurring events over time. In this work, we show how to improve the training and inference of SA models by decoupling their full expression into (1) an aggregated baseline hazard, which captures the overall behavior of a given population, and (2) independently distributed survival scores, which model idiosyncratic probabilistic dynamics of its given members, in a fully parametric setting. The proposed inference method is shown to dynamically handle right-censored observation horizons, and to achieve competitive performance when compared to other state-of-the-art methods in a variety of real-world datasets, including computationally inefficient Deep Learning-based SA methods and models that require MCMC for inference. Nevertheless, our method achieves robust results from the outset, while not being subjected to fine-tuning or hyperparameter optimization.
In software engineering, the meticulous configuration of software tools is crucial in ensuring optimal performance within intricate systems. However, the complexity inherent in selecting optimal configurations is exacerbated by the high-dimensional search spaces presented in modern applications. Conventional trial-and-error or intuition-driven methods are both inefficient and error-prone, impeding scalability and reproducibility. In this study, we embark on an exploration of leveraging Large-Language Models (LLMs) to streamline the software configuration process. We identify that the task of hyperparameter configuration for machine learning components within intelligent applications is particularly challenging due to the extensive search space and performance-critical nature. Existing methods, including Bayesian optimization, have limitations regarding initial setup, computational cost, and convergence efficiency. Our work presents a novel approach that employs LLMs, such as Chat-GPT, to identify starting conditions and narrow down the search space, improving configuration efficiency. We conducted a series of experiments to investigate the variability of LLM-generated responses, uncovering intriguing findings such as potential response caching and consistent behavior based on domain-specific keywords. Furthermore, our results from hyperparameter optimization experiments reveal the potential of LLMs in expediting initialization processes and optimizing configurations. While our initial insights are promising, they also indicate the need for further in-depth investigations and experiments in this domain.
Hyperparameters of Deep Learning (DL) pipelines are crucial for their downstream performance. While a large number of methods for Hyperparameter Optimization (HPO) have been developed, their incurred costs are often untenable for modern DL. Consequently, manual experimentation is still the most prevalent approach to optimize hyperparameters, relying on the researcher's intuition, domain knowledge, and cheap preliminary explorations. To resolve this misalignment between HPO algorithms and DL researchers, we propose PriorBand, an HPO algorithm tailored to DL, able to utilize both expert beliefs and cheap proxy tasks. Empirically, we demonstrate PriorBand's efficiency across a range of DL benchmarks and show its gains under informative expert input and robustness against poor expert beliefs
This paper explores the use of foundational large language models (LLMs) in hyperparameter optimization (HPO). Hyperparameters are critical in determining the effectiveness of machine learning models, yet their optimization often relies on manual approaches in limited-budget settings. By prompting LLMs with dataset and model descriptions, we develop a methodology where LLMs suggest hyperparameter configurations, which are iteratively refined based on model performance. Our empirical evaluations on standard benchmarks reveal that within constrained search budgets, LLMs can match or outperform traditional HPO methods like Bayesian optimization across different models on standard benchmarks. Furthermore, we propose to treat the code specifying our model as a hyperparameter, which the LLM outputs and affords greater flexibility than existing HPO approaches.
Through additional training, we explore embedding specialized scientific knowledge into the Llama 2 Large Language Model (LLM). Key findings reveal that effective knowledge integration requires reading texts from multiple perspectives, especially in instructional formats. We utilize text augmentation to tackle the scarcity of specialized texts, including style conversions and translations. Hyperparameter optimization proves crucial, with different size models (7b, 13b, and 70b) reasonably undergoing additional training. Validating our methods, we construct a dataset of 65,000 scientific papers. Although we have succeeded in partially embedding knowledge, the study highlights the complexities and limitations of incorporating specialized information into LLMs, suggesting areas for further improvement.
The fine-tuning of Large Language Models (LLMs) has enabled them to recently achieve milestones in natural language processing applications. The emergence of ever larger LLMs has paved the way for more efficient fine-tuning methods. Among these, the Low-Rank Adaptation (LoRA) method keeps most of the weights of the pre-trained LLM frozen while introducing a low-rank decomposition of the weight matrix, enabling the tuning of only a very small proportion of the network. The performance on downstream tasks of models fine-tuned with LoRA heavily relies on a set of hyperparameters including the rank of the decomposition. In this work, we investigate the choice of these hyperparameters through two main blackbox optimization (BBO) techniques. We examine the whole pipeline of performing fine-tuning and validation on a pre-trained LLM as a blackbox and efficiently explore the space of hyperparameters with the \nomad algorithm, achieving a boost in performance and human alignment of the tuned model.
Hyperparameter Optimization (HPO) of Deep Learning-based models tends to be a compute resource intensive process as it usually requires to train the target model with many different hyperparameter configurations. We show that integrating model performance prediction with early stopping methods holds great potential to speed up the HPO process of deep learning models. Moreover, we propose a novel algorithm called Swift-Hyperband that can use either classical or quantum support vector regression for performance prediction and benefit from distributed High Performance Computing environments. This algorithm is tested not only for the Machine-Learned Particle Flow model used in High Energy Physics, but also for a wider range of target models from domains such as computer vision and natural language processing. Swift-Hyperband is shown to find comparable (or better) hyperparameters as well as using less computational resources in all test cases.
Monitoring wildfires is an essential step in minimizing their impact on the planet, understanding the many negative environmental, economic, and social consequences. Recent advances in remote sensing technology combined with the increasing application of artificial intelligence methods have improved real-time, high-resolution fire monitoring. This study explores two proposed approaches based on the U-Net model for automating and optimizing the burned-area mapping process. Denoted 128 and AllSizes (AS), they are trained on datasets with a different class balance by cropping input images to different sizes. They are then applied to Landsat imagery and time-series data from two fire-prone regions in Chile. The results obtained after enhancement of model performance by hyperparameter optimization demonstrate the effectiveness of both approaches. Tests based on 195 representative images of the study area show that increasing dataset balance using the AS model yields better performance. More specifically, AS exhibited a Dice Coefficient (DC) of 0.93, an Omission Error (OE) of 0.086, and a Commission Error (CE) of 0.045, while the 128 model achieved a DC of 0.86, an OE of 0.12, and a CE of 0.12. These findings should provide a basis for further development of scalable automatic burned-area mapping tools.
We run an independent comparison of all hyperparameter optimization (hyperopt) engines available in the Ray Tune library. We introduce two ways to normalize and aggregate statistics across data sets and models, one rank-based, and another one sandwiching the score between the random search score and the full grid search score. This affords us i) to rank the hyperopt engines, ii) to make generalized and statistically significant statements on how much they improve over random search, and iii) to make recommendations on which engine should be used to hyperopt a given learning algorithm. We find that most engines beat random search, but that only three of them (HEBO, AX, and BlendSearch) clearly stand out. We also found that some engines seem to specialize in hyperopting certain learning algorithms, which makes it tricky to use hyperopt in comparison studies, since the choice of the hyperopt technique may favor some of the models in the comparison.
Previous efforts on hyperparameter optimization (HPO) of machine learning (ML) models predominately focus on algorithmic advances, yet little is known about the topography of the underlying hyperparameter (HP) loss landscape, which plays a fundamental role in governing the search process of HPO. While several works have conducted fitness landscape analysis (FLA) on various ML systems, they are limited to properties of isolated landscape without interrogating the potential structural similarities among them. The exploration of such similarities can provide a novel perspective for understanding the mechanism behind modern HPO methods, but has been missing, possibly due to the expensive cost of large-scale landscape construction, and the lack of effective analysis methods. In this paper, we mapped 1,500 HP loss landscapes of 6 representative ML models on 63 datasets across different fidelity levels, with 11M+ configurations. By conducting exploratory analysis on these landscapes with fine-grained visualizations and dedicated FLA metrics, we observed a similar landscape topography across a wide range of models, datasets, and fidelities, and shed light on several central topics in HPO.