We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning, including hyperparameter optimization, loss function learning, few-shot learning, invariance learning and more. These problems are often formalized as Bi-Level optimizations (BLO). We introduce a novel perspective by turning a given BLO problem into a stochastic optimization, where the inner loss function becomes a smooth probability distribution, and the outer loss becomes an expected loss over the inner distribution. To solve this stochastic optimization, we adopt Stochastic Gradient Langevin Dynamics (SGLD) MCMC to sample inner distribution, and propose a recurrent algorithm to compute the MC-estimated hypergradient. Our derivation is similar to forward-mode differentiation, but we introduce a new first-order approximation that makes it feasible for large models without needing to store huge Jacobian matrices. The main benefits are two-fold: i) Our stochastic formulation takes into account uncertainty, which makes the method robust to suboptimal inner optimization or non-unique multiple inner minima due to overparametrization; ii) Compared to existing methods that often exhibit unstable behavior and hyperparameter sensitivity in practice, our method leads to considerably more reliable solutions. We demonstrate that the new approach achieves promising results on diverse meta learning problems and easily scales to learning 87M hyperparameters in the case of Vision Transformers.
Bayesian Optimization is ubiquitous in the field of experimental design and blackbox optimization for improving search efficiency, but has been traditionally restricted to regression models which are only applicable to fixed search spaces and tabular input features. We propose Embed-then-Regress, a paradigm for applying in-context regression over string inputs, through the use of string embedding capabilities of pretrained language models. By expressing all inputs as strings, we are able to perform general-purpose regression for Bayesian Optimization over various domains including synthetic, combinatorial, and hyperparameter optimization, obtaining comparable results to state-of-the-art Gaussian Process-based algorithms. Code can be found at https://github.com/google-research/optformer/tree/main/optformer/embed_then_regress.
Pumpkin is a vital crop cultivated globally, and its productivity is crucial for food security, especially in developing regions. Accurate and timely detection of pumpkin leaf diseases is essential to mitigate significant losses in yield and quality. Traditional methods of disease identification rely heavily on subjective judgment by farmers or experts, which can lead to inefficiencies and missed opportunities for intervention. Recent advancements in machine learning and deep learning offer promising solutions for automating and improving the accuracy of plant disease detection. This paper presents a comprehensive analysis of state-of-the-art Convolutional Neural Network (CNN) models for classifying diseases in pumpkin plant leaves. Using a publicly available dataset of 2000 highresolution images, we evaluate the performance of several CNN architectures, including ResNet, DenseNet, and EfficientNet, in recognizing five classes: healthy leaves and four common diseases downy mildew, powdery mildew, mosaic disease, and bacterial leaf spot. We fine-tuned these pretrained models and conducted hyperparameter optimization experiments. ResNet-34, DenseNet-121, and EfficientNet-B7 were identified as top-performing models, each excelling in different classes of leaf diseases. Our analysis revealed DenseNet-121 as the optimal model when considering both accuracy and computational complexity achieving an overall accuracy of 86%. This study underscores the potential of CNNs in automating disease diagnosis for pumpkin plants, offering valuable insights that can contribute to enhancing agricultural productivity and minimizing economic losses.
Hyperparameter optimization is an essential component in many data science pipelines and typically entails exhaustive time and resource-consuming computations in order to explore the combinatorial search space. Similar to this problem, other key operations in data science pipelines exhibit the exact same properties. Important examples are: neural architecture search, where the goal is to identify the best design choices for a neural network, and query cardinality estimation, where given different predicate values for a SQL query the goal is to estimate the size of the output. In this paper, we abstract away those essential components of data science pipelines and we model them as instances of tensor completion, where each variable of the search space corresponds to one mode of the tensor, and the goal is to identify all missing entries of the tensor, corresponding to all combinations of variable values, starting from a very small sample of observed entries. In order to do so, we first conduct a thorough experimental evaluation of existing state-of-the-art tensor completion techniques and introduce domain-inspired adaptations (such as smoothness across the discretized variable space) and an ensemble technique which is able to achieve state-of-the-art performance. We extensively evaluate existing and proposed methods in a number of datasets generated corresponding to (a) hyperparameter optimization for non-neural network models, (b) neural architecture search, and (c) variants of query cardinality estimation, demonstrating the effectiveness of tensor completion as a tool for automating data science pipelines. Furthermore, we release our generated datasets and code in order to provide benchmarks for future work on this topic.
In a world burdened by air pollution, the integration of state-of-the-art sensor calibration techniques utilizing Quantum Computing (QC) and Machine Learning (ML) holds promise for enhancing the accuracy and efficiency of air quality monitoring systems in smart cities. This article investigates the process of calibrating inexpensive optical fine-dust sensors through advanced methodologies such as Deep Learning (DL) and Quantum Machine Learning (QML). The objective of the project is to compare four sophisticated algorithms from both the classical and quantum realms to discern their disparities and explore possible alternative approaches to improve the precision and dependability of particulate matter measurements in urban air quality surveillance. Classical Feed-Forward Neural Networks (FFNN) and Long Short-Term Memory (LSTM) models are evaluated against their quantum counterparts: Variational Quantum Regressors (VQR) and Quantum LSTM (QLSTM) circuits. Through meticulous testing, including hyperparameter optimization and cross-validation, the study assesses the potential of quantum models to refine calibration performance. Our analysis shows that: the FFNN model achieved superior calibration accuracy on the test set compared to the VQR model in terms of lower L1 loss function (2.92 vs 4.81); the QLSTM slightly outperformed the LSTM model (loss on the test set: 2.70 vs 2.77), despite using fewer trainable weights (66 vs 482).
Knowledge graph (KG) completion aims to identify additional facts that can be inferred from the existing facts in the KG. Recent developments in this field have explored this task in the inductive setting, where at test time one sees entities that were not present during training; the most performant models in the inductive setting have employed path encoding modules in addition to standard subgraph encoding modules. This work similarly focuses on KG completion in the inductive setting, without the explicit use of path encodings, which can be time-consuming and introduces several hyperparameters that require costly hyperparameter optimization. Our approach uses a Transformer-based subgraph encoding module only; we introduce connection-biased attention and entity role embeddings into the subgraph encoding module to eliminate the need for an expensive and time-consuming path encoding module. Evaluations on standard inductive KG completion benchmark datasets demonstrate that our \textbf{C}onnection-\textbf{B}iased \textbf{Li}nk \textbf{P}rediction (CBLiP) model has superior performance to models that do not use path information. Compared to models that utilize path information, CBLiP shows competitive or superior performance while being faster. Additionally, to show that the effectiveness of connection-biased attention and entity role embeddings also holds in the transductive setting, we compare CBLiP's performance on the relation prediction task in the transductive setting.
Hyperparameters are a critical factor in reliably training well-performing reinforcement learning (RL) agents. Unfortunately, developing and evaluating automated approaches for tuning such hyperparameters is both costly and time-consuming. As a result, such approaches are often only evaluated on a single domain or algorithm, making comparisons difficult and limiting insights into their generalizability. We propose ARLBench, a benchmark for hyperparameter optimization (HPO) in RL that allows comparisons of diverse HPO approaches while being highly efficient in evaluation. To enable research into HPO in RL, even in settings with low compute resources, we select a representative subset of HPO tasks spanning a variety of algorithm and environment combinations. This selection allows for generating a performance profile of an automated RL (AutoRL) method using only a fraction of the compute previously necessary, enabling a broader range of researchers to work on HPO in RL. With the extensive and large-scale dataset on hyperparameter landscapes that our selection is based on, ARLBench is an efficient, flexible, and future-oriented foundation for research on AutoRL. Both the benchmark and the dataset are available at https://github.com/automl/arlbench.
The automation of feature extraction of machine learning has been successfully realized by the explosive development of deep learning. However, the structures and hyperparameters of deep neural network architectures also make huge difference on the performance in different tasks. The process of exploring optimal structures and hyperparameters often involves a lot of tedious human intervene. As a result, a legitimate question is to ask for the automation of searching for optimal network structures and hyperparameters. The work of automation of exploring optimal hyperparameters is done by Hyperparameter Optimization. Neural Architecture Search is aimed to automatically find the best network structure given specific tasks. In this paper, we firstly introduced the overall development of Neural Architecture Search and then focus mainly on providing an overall and understandable survey about Neural Architecture Search works that are relevant with reinforcement learning, including improvements and variants based on the hope of satisfying more complex structures and resource-insufficient environment.
In the AutoML domain, test accuracy is heralded as the quintessential metric for evaluating model efficacy, underpinning a wide array of applications from neural architecture search to hyperparameter optimization. However, the reliability of test accuracy as the primary performance metric has been called into question, notably through research highlighting how label noise can obscure the true ranking of state-of-the-art models. We venture beyond, along another perspective where the existence of hard samples within datasets casts further doubt on the generalization capabilities inferred from test accuracy alone. Our investigation reveals that the distribution of hard samples between training and test sets affects the difficulty levels of those sets, thereby influencing the perceived generalization capability of models. We unveil two distinct generalization pathways-toward easy and hard samples-highlighting the complexity of achieving balanced model evaluation. Finally, we propose a benchmarking procedure for comparing hard sample identification methods, facilitating the advancement of more nuanced approaches in this area. Our primary goal is not to propose a definitive solution but to highlight the limitations of relying primarily on test accuracy as an evaluation metric, even when working with balanced datasets, by introducing the in-class data imbalance problem. By doing so, we aim to stimulate a critical discussion within the research community and open new avenues for research that consider a broader spectrum of model evaluation criteria. The anonymous code is available at https://github.com/PawPuk/CurvBIM blueunder the GPL-3.0 license.
Inference-time techniques are emerging as highly effective tools to enhance large language model (LLM) capabilities. However, best practices for developing systems that combine these techniques remain underdeveloped due to our limited understanding of the utility of individual inference-time techniques and the interactions between them. Additionally, efficiently and automatically searching the space of model choices, inference-time techniques, and their compositions is challenging due to the large design space. To address these challenges, we introduce Archon, a modular framework for selecting, combining, and stacking layers of inference-time techniques to construct optimized LLM systems for target benchmarks. Rather than relying on a single LLM called once, we leverage a diverse set of LLMs and inference-time techniques, creating LLM systems greater than the sum of their parts. Archon defines an extensible design space, encompassing techniques such as generation ensembling, repeated sampling, ranking, fusion, critiquing, verification, and unit testing. It transforms the problem of building LLM systems into a hyperparameter optimization objective. Given the available LLMs, inference-time techniques, and compute budget, Archon utilizes hyperparameter search techniques to discover optimized architectures for target benchmark(s). We evaluate Archon architectures across a range of instruction-following, reasoning, and coding benchmarks, including MT-Bench, Arena-Hard-Auto, AlpacaEval 2.0, MixEval, MixEval Hard, MATH, and CodeContests. Archon architectures outperform frontier models, such as GPT-4o and Claude 3.5 Sonnet, on these benchmarks, achieving an average accuracy increase of 15.1 percentage points by using all available LLMs. We make our code and datasets available publicly on Github: https://github.com/ScalingIntelligence/Archon.
Learning rate is a crucial parameter in training of neural networks. A properly tuned learning rate leads to faster training and higher test accuracy. In this paper, we propose a Lipschitz bandit-driven approach for tuning the learning rate of neural networks. The proposed approach is compared with the popular HyperOpt technique used extensively for hyperparameter optimization and the recently developed bandit-based algorithm BLiE. The results for multiple neural network architectures indicate that our method finds a better learning rate using a) fewer evaluations and b) lesser number of epochs per evaluation, when compared to both HyperOpt and BLiE. Thus, the proposed approach enables more efficient training of neural networks, leading to lower training time and lesser computational cost.
Bilevel optimization methods are increasingly relevant within machine learning, especially for tasks such as hyperparameter optimization and meta-learning. Compared to the offline setting, online bilevel optimization (OBO) offers a more dynamic framework by accommodating time-varying functions and sequentially arriving data. This study addresses the online nonconvex-strongly convex bilevel optimization problem. In deterministic settings, we introduce a novel online Bregman bilevel optimizer (OBBO) that utilizes adaptive Bregman divergences. We demonstrate that OBBO enhances the known sublinear rates for bilevel local regret through a novel hypergradient error decomposition that adapts to the underlying geometry of the problem. In stochastic contexts, we introduce the first stochastic online bilevel optimizer (SOBBO), which employs a window averaging method for updating outer-level variables using a weighted average of recent stochastic approximations of hypergradients. This approach not only achieves sublinear rates of bilevel local regret but also serves as an effective variance reduction strategy, obviating the need for additional stochastic gradient samples at each timestep. Experiments on online hyperparameter optimization and online meta-learning highlight the superior performance, efficiency, and adaptability of our Bregman-based algorithms compared to established online and offline bilevel benchmarks.
In this paper, we present a cross-entropy optimization method for hyperparameter optimization in stochastic gradient-based approaches to train deep neural networks. The value of a hyperparameter of a learning algorithm often has great impact on the performance of a model such as the convergence speed, the generalization performance metrics, etc. While in some cases the hyperparameters of a learning algorithm can be part of learning parameters, in other scenarios the hyperparameters of a stochastic optimization algorithm such as Adam [5] and its variants are either fixed as a constant or are kept changing in a monotonic way over time. We give an in-depth analysis of the presented method in the framework of expectation maximization (EM). The presented algorithm of cross-entropy optimization for hyperparameter optimization of a learning algorithm (CEHPO) can be equally applicable to other areas of optimization problems in deep learning. We hope that the presented methods can provide different perspectives and offer some insights for optimization problems in different areas of machine learning and beyond.
Quick and reliable measurement of wood chip moisture content is an everlasting problem for numerous forest-reliant industries such as biofuel, pulp and paper, and bio-refineries. Moisture content is a critical attribute of wood chips due to its direct relationship with the final product quality. Conventional techniques for determining moisture content, such as oven-drying, possess some drawbacks in terms of their time-consuming nature, potential sample damage, and lack of real-time feasibility. Furthermore, alternative techniques, including NIR spectroscopy, electrical capacitance, X-rays, and microwaves, have demonstrated potential; nevertheless, they are still constrained by issues related to portability, precision, and the expense of the required equipment. Hence, there is a need for a moisture content determination method that is instant, portable, non-destructive, inexpensive, and precise. This study explores the use of deep learning and machine vision to predict moisture content classes from RGB images of wood chips. A large-scale image dataset comprising 1,600 RGB images of wood chips has been collected and annotated with ground truth labels, utilizing the results of the oven-drying technique. Two high-performing neural networks, MoistNetLite and MoistNetMax, have been developed leveraging Neural Architecture Search (NAS) and hyperparameter optimization. The developed models are evaluated and compared with state-of-the-art deep learning models. Results demonstrate that MoistNetLite achieves 87% accuracy with minimal computational overhead, while MoistNetMax exhibits exceptional precision with a 91% accuracy in wood chip moisture content class prediction. With improved accuracy and faster prediction speed, our proposed MoistNet models hold great promise for the wood chip processing industry.
The rapid evolution of mobile networks from 5G to 6G has necessitated the development of autonomous network management systems, such as Zero-Touch Networks (ZTNs). However, the increased complexity and automation of these networks have also escalated cybersecurity risks. Existing Intrusion Detection Systems (IDSs) leveraging traditional Machine Learning (ML) techniques have shown effectiveness in mitigating these risks, but they often require extensive manual effort and expert knowledge. To address these challenges, this paper proposes an Automated Machine Learning (AutoML)-based autonomous IDS framework towards achieving autonomous cybersecurity for next-generation networks. To achieve autonomous intrusion detection, the proposed AutoML framework automates all critical procedures of the data analytics pipeline, including data pre-processing, feature engineering, model selection, hyperparameter tuning, and model ensemble. Specifically, it utilizes a Tabular Variational Auto-Encoder (TVAE) method for automated data balancing, tree-based ML models for automated feature selection and base model learning, Bayesian Optimization (BO) for hyperparameter optimization, and a novel Optimized Confidence-based Stacking Ensemble (OCSE) method for automated model ensemble. The proposed AutoML-based IDS was evaluated on two public benchmark network security datasets, CICIDS2017 and 5G-NIDD, and demonstrated improved performance compared to state-of-the-art cybersecurity methods. This research marks a significant step towards fully autonomous cybersecurity in next-generation networks, potentially revolutionizing network security applications.
Heart failure affects millions of people worldwide, significantly reducing quality of life and leading to high mortality rates. Despite extensive research, the relationship between heart failure and mortality rates among ICU patients is not fully understood, indicating the need for more accurate prediction models. This study analyzed data from 1,177 patients over 18 years old from the MIMIC-III database, identified using ICD-9 codes. Preprocessing steps included handling missing data, removing duplicates, treating skewness, and using oversampling techniques to address data imbalances. Through rigorous feature selection using Variance Inflation Factor (VIF), expert clinical input, and ablation studies, 46 key features were identified to enhance model performance. Our analysis compared several machine learning models, including Logistic Regression, Support Vector Machine (SVM), Random Forest, LightGBM, and XGBoost. XGBoost emerged as the superior model, achieving a test AUC-ROC of 0.9228 (95\% CI 0.8748 - 0.9613), significantly outperforming our previous work (AUC-ROC of 0.8766) and the best results reported in existing literature (AUC-ROC of 0.824). The improved model's success is attributed to advanced feature selection methods, robust preprocessing techniques, and comprehensive hyperparameter optimization through Grid-Search. SHAP analysis and feature importance evaluations based on XGBoost highlighted key variables like leucocyte count and RDW, providing valuable insights into the clinical factors influencing mortality risk. This framework offers significant support for clinicians, enabling them to identify high-risk ICU heart failure patients and improve patient outcomes through timely and informed interventions.
Hyperparameter optimization (HPO) and neural architecture search (NAS) are powerful in attaining state-of-the-art machine learning models, with Bayesian optimization (BO) standing out as a mainstream method. Extending BO into the multi-fidelity setting has been an emerging research topic, but faces the challenge of determining an appropriate fidelity for each hyperparameter configuration to fit the surrogate model. To tackle the challenge, we propose a multi-fidelity BO method named FastBO, which adaptively decides the fidelity for each configuration and efficiently offers strong performance. The advantages are achieved based on the novel concepts of efficient point and saturation point for each configuration.We also show that our adaptive fidelity identification strategy provides a way to extend any single-fidelity method to the multi-fidelity setting, highlighting its generality and applicability.
Advancing Machine Learning (ML)-based perception models for autonomous systems necessitates addressing weak spots within the models, particularly in challenging Operational Design Domains (ODDs). These are environmental operating conditions of an autonomous vehicle which can contain difficult conditions, e.g., lens flare at night or objects reflected in a wet street. This report introduces a novel methodology for training with augmentations to enhance model robustness and performance in such conditions. The proposed approach leverages customized physics-based augmentation functions, to generate realistic training data that simulates diverse ODD scenarios. We present a comprehensive framework that includes identifying weak spots in ML models, selecting suitable augmentations, and devising effective training strategies. The methodology integrates hyperparameter optimization and latent space optimization to fine-tune augmentation parameters, ensuring they maximally improve the ML models' performance. Experimental results demonstrate improvements in model performance, as measured by commonly used metrics such as mean Average Precision (mAP) and mean Intersection over Union (mIoU) on open-source object detection and semantic segmentation models and datasets. Our findings emphasize that optimal training strategies are model- and data-specific and highlight the benefits of integrating augmentations into the training pipeline. By incorporating augmentations, we observe enhanced robustness of ML-based perception models, making them more resilient to edge cases encountered in real-world ODDs. This work underlines the importance of customized augmentations and offers an effective solution for improving the safety and reliability of autonomous driving functions.
This project explores the integration of Bayesian Optimization (BO) algorithms into a base machine learning model, specifically Convolutional Neural Networks (CNNs), for classifying gravitational waves among background noise. The primary objective is to evaluate whether optimizing hyperparameters using Bayesian Optimization enhances the base model's performance. For this purpose, a Kaggle [1] dataset that comprises real background noise (labeled 0) and simulated gravitational wave signals with noise (labeled 1) is used. Data with real noise is collected from three detectors: LIGO Livingston, LIGO Hanford, and Virgo. Through data preprocessing and training, the models effectively classify testing data, predicting the presence of gravitational wave signals with a remarkable score, of 83.61%. The BO model demonstrates comparable accuracy to the base model, but its performance improvement is not very significant (84.34%). However, it is worth noting that the BO model needs additional computational resources and time due to the iterations required for hyperparameter optimization, requiring additional training on the entire dataset. For this reason, the BO model is less efficient in terms of resources compared to the base model in gravitational wave classification
The study emphasizes the challenge of finding the optimal trade-off between bias and variance, especially as hyperparameter optimization increases in complexity. Through empirical analysis, three hyperparameter tuning algorithms Tree-structured Parzen Estimator (TPE), Genetic Search, and Random Search are evaluated across regression and classification tasks. The results show that nonlinear models, with properly tuned hyperparameters, significantly outperform linear models. Interestingly, Random Search excelled in regression tasks, while TPE was more effective for classification tasks. This suggests that there is no one-size-fits-all solution, as different algorithms perform better depending on the task and model type. The findings underscore the importance of selecting the appropriate tuning method and highlight the computational challenges involved in optimizing machine learning models, particularly as search spaces expand.