MLPerf benchmarks ML inference systems across diverse hardware.
problem Challenges in evaluating ML inference systems due to variety and complexity.
method MLPerf prescribes a set of rules and best practices for comparability.
result First call for submissions yielded over 600 reproducible measurements.
Machine learning (ML) needs industry-standard performance benchmarks to support design and competitive evaluation of the many emerging software and hardware solutions for ML. But ML training presents three unique benchmarking challenges absent from other domains: optimizations that improve training throughput can incre…
ABOUT ML aims to improve transparency in ML lifecycle documentation.
problem Lack of standard documentation in machine learning lifecycle.
method Initiative to operationalize ML transparency and standardize documentation.
result Helps address gaps in ML lifecycle documentation.
Review and benchmark 58 feature selection methods for ML applications.
problem Selecting appropriate features for predictive modeling in ML applications.
method Synthesizes literature on feature selection benchmarking and evaluates 58 methods.
result Well-performing candidate methods identified: random forest, DISR, JIM.
New IRT method identifies useful datasets for ML classifier evaluation.
problem Lack of standard evaluation strategy for ML benchmarks.
method Applied Item Response Theory (IRT) to OpenML-CC18 benchmark.
result Not all datasets are useful for evaluating classifiers.
ClimART dataset benchmarks ML emulators for atmospheric RT in climate models.
problem Lack of a comprehensive dataset and standardized practices for ML benchmarking in climate models.
method Builds ClimART, a large dataset with over 10 million samples, and presents novel baselines.
result Indicates shortcomings of prior datasets and network architectures.
DIGEN benchmark provides synthetic datasets for ML algorithm evaluation.
problem Understanding and comparing machine learning algorithms' performance.
method Synthetic datasets generated using 40 mathematical functions to evaluate machine learning algorithms.
result DIGEN resource facilitates understanding why algorithms perform poorly and provides ideas for improvement.
OGB provides diverse graph datasets for robust ML research.
problem Challenges in scalable and robust graph machine learning.
method Unified evaluation protocol, diverse datasets, and automated pipeline.
result Significant scalability and generalization challenges identified.
CodeReef enables sharing ML models across platforms efficiently.
problem Sharing and deploying ML models across different systems efficiently.
method Developed an open platform to share ML components, automate deployment, and benchmark models.
result Demonstrated efficient deployment and benchmarking of ML models across diverse platforms.
MLModelScope streamlines ML/DL model evaluation and benchmarking.
problem Challenges in evaluating and benchmarking ML/DL models.
method Open-source, framework/hardware agnostic platform with distributed design.
result Demonstrates the impact of model evaluation pipelines and HW/SW choices.
FLAIR dataset for federated learning benchmarks.
problem Lack of suitable federated learning datasets.
method Curated large-scale annotated image dataset for multi-label classification.
result FLAIR captures real-world federated learning challenges.
Paper compiles ML algorithm performance benchmarks on OpenML datasets.
problem Finding optimal hyperparameters for ML algorithms efficiently.
method Generated benchmark data for 7 ML algorithms on 39 datasets, fixed hyperparameters before testing.
result Comprehensive dataset of ML algorithm performance sensitivity.
SurvSet offers a repository of 76 T2E datasets for ML benchmarking.
problem Lack of open-source T2E dataset repositories for ML benchmarking.
method Consistent formatting of datasets for various ML algorithms and statistical methods.
result SurvSet provides a comprehensive resource for T2E analysis.
Framework optimizes cloud container sizing for ML tasks.
problem Challenges in cloud container configuration for ML services.
method Autonomous scaling using nested-loop Monte Carlo simulation.
result Reduces compute cost and accelerates ML algorithms.
Machine learning (ML) has become a vital part in many aspects of our daily life. However, building well performing machine learning applications requires highly specialized data scientists and domain experts. Automated machine learning (AutoML) aims to reduce the demand for data scientists by enabling domain experts to…
When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond? Through scenarios grounded in adversarial ML literature, we explore how some aspects of computer crime, copyright, and tort law interface with perturbation, poisoning, model stealing and model inversion…
HAR model outperforms ML in stock forecasting with correct fitting schemes.
problem Realized volatility forecasting using machine learning techniques.
method Investigated the role of fitting schemes in HAR model performance, focusing on training window and re-estimation frequency.
result HAR model consistently outperforms ML models when using a correctly specified fitting approach.
Over the last several years, the use of machine learning (ML) in neuroscience has been rapidly increasing. Here, we review ML's contributions, both realized and potential, across several areas of systems neuroscience. We describe four primary roles of ML within neuroscience: 1) creating solutions to engineering problem…
Propose an XMSE-aware mixed estimator for EB that interpolates between ML and EB shrinkage.
problem Kernel-based EB estimation may be worse than ML when the kernel is poorly aligned with the true parameter.
method An XMSE-aware mixed estimator that interpolates between ML and EB shrinkage.
result Fixed-weight XMSE is a scalar quadratic, yielding a closed-form oracle mixing weight that is no worse than both ML and the base EB estimator at the XMSE scale.
Study finds physical priors don't significantly improve ML models for learning latent dynamics.
problem Learning latent dynamics from visual observations without access to the underlying state.
method Benchmarked 17 datasets with visual observations of physical systems using various physically inspired methods alongside baselines.
result Physical priors do not significantly improve standard techniques for learning latent dynamics.
Study investigates OOD generalization methods for mechanics problems.
problem Real-world mechanics problems with unknown test environments and data distribution shifts.
method Investigates OOD generalization methods for regression problems in mechanics.
result OOD generalization methods perform better than traditional ML methods on mechanics-specific regression problems.
The development of accurate and transferable machine learning (ML) potentials for predicting molecular energetics is a challenging task. The process of data generation to train such ML potentials is a task neither well understood nor researched in detail. In this work, we present a fully automated approach for the gene…
New framework assesses and benchmarks ML methods for multivariate time series.
problem Benchmarking and explaining performance of machine learning methods.
method Proposes a new framework with systematized performance-explainability characteristics.
result Illustrates application to multivariate time series classifiers.
A ML model accurately replicates chaotic dynamics across various parameters.
problem Replicating chaotic characteristics of non-linear dynamics using machine learning.
method A ML model trained to predict one-step-ahead states from historic states captures bifurcation diagrams and Lyapunov exponents universally.
result Variational quantum circuit outperforms classical models in reproducing long-term chaotic characteristics.
CHILI datasets tackle inorganic nanomaterials, advancing graph machine learning.
problem Challenges in modelling inorganic crystalline materials and nanomaterials with graph ML.
method Presented two large-scale datasets of inorganic nanomaterials, defined property and structure prediction tasks.
result Benchmarked performance of graph ML methods on inorganic nanomaterials, highlighting areas for future work.
Random number generators (RNGs) that are crucial for cryptographic applications have been the subject of adversarial attacks. These attacks exploit environmental information to predict generated random numbers that are supposed to be truly random and unpredictable. Though quantum random number generators (QRNGs) are ba…
This paper compares ML algorithms for PD prediction, finding XGBoost to be the most effective.
problem Predicting the probability of default in loan portfolios.
method Comparison of five ML algorithms (Random Forests, Decision Trees, XGBoost, Gradient Boosting, AdaBoost) with logistic regression.
result XGBoost outperforms other ML algorithms for PD prediction.
This paper predicts weekly stock market movements using machine learning and introduces a new benchmark.
problem Predicting stock market movements using daily data and various ML models.
method Focuses on weekly movements, introduces random traders as a benchmark, uses additional features, and adjusts training datasets.
result Trained models, especially MLP, show good performance across different trends.
Develops fair feature importance scores for tree-based models to interpret fairness.
problem Ensuring fairness in machine learning models, especially tree-based ones.
method Inspired by decision trees, proposes a novel fair feature importance score based on mean decrease in group bias.
result Valid interpretations of fairness for tree-based ensembles and surrogates of other ML systems.
CausalBench aims to advance causal learning research with a transparent platform.
problem Lack of unified benchmark datasets, algorithms, metrics, and evaluation interfaces for causal learning.
method Introduces CausalBench, a flexible benchmark framework for causal analysis and machine learning.
result Promotes scientific collaboration, reproducibility, and awareness in causal learning research.
Machine learning (ML) started to become widely deployed in cyber security settings for shortening the detection cycle of cyber attacks. To date, most ML-based systems are either proprietary or make specific choices of feature representations and machine learning models. The success of these techniques is difficult to a…
Floods are among the most destructive natural disasters, which are highly complex to model. The research on the advancement of flood prediction models contributed to risk reduction, policy suggestion, minimization of the loss of human life, and reduction the property damage associated with floods. To mimic the complex …
The paper proposes a method to evaluate ML models for subjective inference, focusing on sentence toxicity.
problem Bias in ML models for subjective inference, especially in real-life applications.
method Proposes a list of specifications to evaluate ML models for subjective inference, illustrated with a sentence toxicity example.
result Demonstrates the importance of considering subjectivity and bias in evaluating ML models.
The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the eno…
New insights into ML models' accuracy and generalization for scientific problems.
problem Quantifying accuracy and generalization of ML models in scientific applications.
method Rigorous numerical analysis and theoretical bounds for linear differential equations.
result Different ML models can have opposing generalization behaviors, contrary to intuition.
In multi-label text classification, each textual document can be assigned with one or more labels. Due to this nature, the multi-label text classification task is often considered to be more challenging compared to the binary or multi-class text classification problems. As an important task with broad applications in b…
Study improves forecasting of ED crowding using advanced ML models.
problem Improving forecasting of emergency department crowding.
method Advanced machine learning models (N-BEATS, LightGBM, DeepAR) using multivariable input data.
result N-BEATS and LightGBM outperform benchmarks in forecasting ED occupancy.
We recently outlined the vision of "Learning Everywhere" which captures the possibility and impact of how learning methods and traditional HPC methods can be coupled together. A primary driver of such coupling is the promise that Machine Learning (ML) will give major performance improvements for traditional HPC simulat…
Modyn automates continuous ML model training on growing datasets.
problem Continuous model retraining is costly and impractical.
method Data-centric ML platform with policies for continuous training.
result Modyn enables high throughput training with sample-level data selection.
Review of mathematical representations for biomolecular data.
problem Complexity and high dimensionality of biomolecular datasets hinder ML applications.
method Developed low-dimensional and scalable mathematical representations using algebraic topology, differential geometry, and graph theory.
result Mathematical representations improve protein-ligand binding predictions and other biomolecular applications.
Proposes a novel Out-of-Bag anomaly detection method for ML systems.
problem Challenges of detecting data anomalies in real-world datasets.
method Model-based approach decomposing unsupervised problem into ensemble models using Out-of-Bag estimates.
result Demonstrates state-of-the-art performance and improved accuracy in ML systems.
Integrates ML with operations knowledge to improve distributional forecasts in healthcare.
problem Challenges of ML in operational settings, especially lack of distributional information and integration of operations literature.
method Introduces Boosted Generalized Normal Distribution (bGND) using gradient boosting with tree learners. result Improves wait and service time forecasting by 6% and 9% compared to ML benchmarks.
We introduce a means of automating machine learning (ML) for big data tasks, by performing scalable stochastic Bayesian optimisation of ML algorithm parameters and hyper-parameters. More often than not, the critical tuning of ML algorithm parameters has relied on domain expertise from experts, along with laborious hand…
Fair active learning selects data points to balance model accuracy and fairness.
problem Ensuring fairness in machine learning models used in high-stakes applications.
method Designing algorithms for fair active learning that select data points to balance model accuracy and fairness.
result Demonstrated the effectiveness and efficiency of fair active learning algorithms over benchmark datasets.
Fair active learning selects data points to balance model accuracy and fairness.
problem Ensuring fairness in machine learning models used in high-stakes applications.
method Designing algorithms for fair active learning that select data points to balance model accuracy and fairness, focusing on demographic parity.
result Demonstrated the effectiveness of the proposed fair active learning approach over benchmark datasets.
AutoML serves as the bridge between varying levels of expertise when designing machine learning systems and expedites the data science process. A wide range of techniques is taken to address this, however there does not exist an objective comparison of these techniques. We present a benchmark of current open source Aut…
Paper assesses holistic risks of inference attacks on ML models.
problem Lack of comprehensive risk assessment of inference attacks on ML models.
method Presented a threat model taxonomy for four inference attacks on five model architectures and four image datasets.
result Complexity of training dataset influences attack performance; model stealing and membership inference attacks are negatively correlated.
Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversar…