Machine learning suffers from poor design, data, and evaluation practices.
problem Ad hoc design, poor data hygiene, and lack of statistical rigor in model evaluation.
method Examines the entire machine learning process from design to evaluation, highlighting common pitfalls and providing recommendations.
result Common pitfalls in machine learning research and development are identified and actionable recommendations are provided.
Model-agnostic interpretation methods can mislead if not used carefully.
problem Misinterpretation of machine learning models due to improper use of techniques.
method General pitfalls of model-agnostic interpretation methods.
result Many pitfalls exist when using global interpretation techniques for machine learning models.
This paper evaluates metrics for graph generative models, addressing common pitfalls.
problem Evaluating and comparing graph generative models effectively.
method Systematic evaluation of MMD, analysis of synthetic and real graphs, practical recommendations.
result MMD can be problematic; practical solutions are provided.
Researchers share pitfalls and improvements in implementing Hinton's capsule network.
problem Implementation pitfalls in Hinton's capsule network hindered progress in the field.
method Identifying and addressing common mistakes in capsule network implementations.
result Improved implementation of Hinton's capsule network outperforms existing open-source implementations.
Deep learning applied to SAR data is explored in this paper.
problem Limited use of deep learning in SAR data processing.
method Introduction to relevant deep learning models, analysis of SAR data characteristics, review of state-of-the-art applications, and future research directions.
result Unlocking the potential of deep learning in SAR data processing.
Humorous article on pitfalls in machine learning research
problem Difficulty in reproducing and validating machine learning results
method Discussion of common issues in machine learning papers
result Highlighting watch out points for researchers
Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls. This article gives numerous examples (which should by no means be construed as an exhaustive lis…
In this paper we sketch some reflections on the pitfalls and inconsistencies of the research program - currently dominant among the profession - aimed at providing microfoundations to macroeconomics along a Walrasian perspective. We argue that such a methodological approach constitutes an unsatisfactory answer to a wel…
Machine learning methods have gained a great deal of popularity in recent years among public administration scholars and practitioners. These techniques open the door to the analysis of text, image and other types of data that allow us to test foundational theories of public administration and to develop new theories. …
Study pitfalls of deep learning ensembles in uncertainty estimation.
problem Pitfalls in in-domain uncertainty estimation and ensembling in deep learning.
method Exploration of standards for uncertainty quantification and broad study of ensembling techniques.
result Many sophisticated ensembling techniques are equivalent to a simple ensemble of few networks.
This paper highlights the overlooked role of preprocessing hyperparameters in machine learning model performance.
problem The neglect of preprocessing hyperparameters in machine learning model evaluation.
method Empirical review and illustration of different procedures for generating and evaluating prediction models.
result Users may fail to report or account for preprocessing hyperparameter optimization, leading to exaggerated performance claims.
The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence indicates that the high predictive performance is often paired with low robustne…
Machine learning aids excited-state molecular dynamics studies.
problem Challenges in studying electronically excited states of molecules.
method Employing machine learning techniques for excited-state molecular dynamics.
result Highlight successes and challenges in machine learning for excited-state processes.
Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that model owners and evaluators are hard-pressed analyzing and studying them. This is exacerbated by the complicated procedures for evaluation. The lack of standard systems and efficient techniques for specifying and pro…
Survey of topological 4-manifold theory, highlighting foundational theorems and pitfalls.
problem Understanding the topological properties of 4-dimensional manifolds.
method Compilation and explanation of foundational theorems, with cautionary notes.
result Many intuitive results in differential topology are not true in the topological category.
Go-Explore improves performance on hard-exploration problems in Atari games.
problem Challenges in reinforcement learning, especially with sparse or deceptive rewards.
method Exploits principles of remembering states, returning to promising states, and solving simulated environments.
result Scores significantly higher than previous state-of-the-art on Montezuma's Revenge and Pitfall.
The paper addresses pitfalls in calibrating option pricing models using deep learning.
problem Calibrating option pricing models to market data using deep learning.
method Identifies and resolves issues in existing approaches, improving model performance and accuracy.
result Proposes solutions that enhance the accuracy and performance of deep learning models in option pricing.
Paper discusses methods to evaluate defenses against adversarial examples.
problem Difficulty in evaluating adversarial robustness.
method Methodological foundations and best practices for evaluating defenses.
result Suggests new methods to avoid common pitfalls in evaluations.
Study identifies pitfalls in assessing hierarchies for multi-class classification.
problem Lack of understanding in selecting hierarchies for multi-class classification.
method Analyzed and compared popular approaches to extracting hierarchies.
result Hierarchy quality becomes irrelevant when using powerful classifiers.
Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low adoption in reinforcement learning research. This difficulty is worsened by the …
Bayesian optimization has emerged as a strong candidate tool for global optimization of functions with expensive evaluation costs. However, due to the dynamic nature of research in Bayesian approaches, and the evolution of computing technology, using Bayesian optimization in a parallel computing environment remains a c…
Model selection is a problem that has occupied machine learning researchers for a long time. Recently, its importance has become evident through applications in deep learning. We propose an agreement-based learning framework that prevents many of the pitfalls associated with model selection. It relies on coupling the t…
Benchmark assesses LLMs' causal inference skills, revealing significant limitations.
problem Lack of rigorous evaluation of LLMs' causal inference capabilities.
method CausalPitfalls benchmark with structured challenges and grading rubrics.
result Significant limitations in current LLMs' statistical causal inference.
NESYM combines AI and Earth models for new climate insights.
problem Replacing traditional Earth models with AI.
method Neural Earth System Modelling (NESYM) integrating AI and climate models.
result Artificial intelligence may render traditional models obsolete.
New categorization of community detection methods to avoid pitfalls.
problem Misuse of community detection methods in practice.
method Descriptive vs. inferential approaches.
result Inferential methods provide clearer insights into network formation.
This review synthesizes uncertainty modeling in probabilistic image segmentation.
problem Relaxed Bayesian assumptions lead to missing uncertainty information in deep models.
method Standardizes theory, notation, and terminology for feature- and parameter-distribution modeling.
result Establishes a common framework for robust decision-making in segmentation tasks.
Bayesian optimization improves molecule design by addressing three pitfalls.
problem Bayesian optimization pitfalls cause poor performance in molecule design.
method Identified and addressed three pitfalls: incorrect prior width, over-smoothing, and inadequate acquisition function maximization.
result Basic BO setup achieves highest performance on PMO benchmark.
Unified framework for ranking-and-selection with multiple correct answers and non-answerable estimates
problem Fixed-precision ranking-and-selection in structured settings with non-unique answers and non-answerable estimates
method Unified framework based on answer-wise acceptance sets, restricted generalized likelihood ratio stopping, and answer-pitfall decomposition
result Unified recipe performs well across a broad range of pure-exploration problems
Nonnegative matrix factorization (NMF) has become a workhorse for signal and data analytics, triggered by its model parsimony and interpretability. Perhaps a bit surprisingly, the understanding to its model identifiability---the major reason behind the interpretability in many applications such as topic mining and hype…
This paper improves conditional sampling for VAEs by overcoming structural issues.
problem Computational intractability of conditional sampling in VAEs.
method Proposes two methods to address pitfalls in Metropolis-within-Gibbs (MWG) for VAEs.
result Improved performance on sampling tasks.
LLMs improve stock price forecasting from financial news and reports.
problem Predicting stock prices with high accuracy and robustness.
method Analyzing financial news, reports, and transcripts using LLMs.
result LLMs can improve stock price forecasting but face practical challenges.
CNNs identify stock market trend endpoints based on expert opinion.
problem Finding optimal entry and exit points for stock market trends.
method Three CNN submodels sequentially identify changepoints, locate them, and classify trends as upward, downward, or flat.
result CNNs can identify long-term trends based on expert opinion, offering a new approach to stock market analysis.
The use of synthetic data generated by Generative Adversarial Networks (GANs) has become quite a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to get more synthetic data that can be used to train downstream classifiers, it is not clear that they re…
This paper evaluates test selection methods for deep neural networks, revealing their limitations.
problem Challenges in testing deep learning systems due to high labeling costs.
method Analysis and empirical testing of 11 test selection methods on five datasets.
result Test selection methods can fail under certain conditions, leading to significant drops in test relative coverage.
Paper proposes decentralized annuities for better retirement security.
problem Current pension systems' limitations and fairness issues.
method Theoretical models and fairness concepts analysis.
result Decentralized annuities offer enhanced flexibility and social welfare.
Cross-validation pitfalls in change-point regression are addressed with new approaches.
problem Cross-validation's prediction error-based criterion may lead to under- or over-estimation of change-points.
method Proposes two approaches: absolute error loss and modified holdout sets.
result Consistent estimation of the number of change-points under certain conditions.
AI methods broaden signal discovery in scientific data.
problem Limited coverage of possible signals in model-dependent searches.
method Model-agnostic AI strategies for broad exploration.
result Enhanced discovery potential in experimental science.
Algorithmic fairness, and in particular the fairness of scoring and classification algorithms, has become a topic of increasing social concern and has recently witnessed an explosion of research in theoretical computer science, machine learning, statistics, the social sciences, and law. Much of the literature considers…
Confirmation bias leads to biased estimates in noisy data analysis.
problem Confirmation bias affects scientific conclusions in noisy data environments.
method Investigation of confirmation bias in Gaussian mixture models using K-means and EM algorithms.
result Estimates from algorithms are biased and resemble initial hypotheses, not the noise.
New findings show a balance between data fit and complexity in kernel hyperparameters.
problem Overcorrelation due to reparametrization of kernel hyperparameters.
method Reparametrization of kernel hyperparameters and analysis of marginal likelihood.
result Data fit term influences all other kernel hyperparameters, not just the complexity penalty.
LLA shows strong performance in Bayesian optimization but has unbounded search space issues.
problem Applying LLA in unbounded search spaces for Bayesian optimization.
method Linearized-Laplace approximation applied to Bayesian optimization problems.
result LLA demonstrates strong performance but also presents unbounded search space challenges.
Develops methods for causal inference in compositional data using instrumental variables.
problem Interpreting summary statistics like diversity indices as causal effects in compositional data.
method Statistical data transformations and regression techniques tailored for compositional data.
result Advantages and limitations of the proposed methods demonstrated on synthetic and real microbiome data.
Machine learning speeds up quantum chemical calculations of excited states.
problem Accurate quantum chemical calculations of excited states are computationally expensive.
method Employing machine learning to speed up and advance excited-state simulations in various fields.
result Machine learning techniques can significantly reduce computational time for excited-state simulations.
New datasets reveal neural networks can rely on simple features, leading to poor generalization.
problem Neural networks' reliance on simple features can lead to poor generalization and robustness.
method Designing datasets with varying levels of simplicity and incorporating non-robustness.
result Neural networks can exclusively rely on the simplest feature, leading to poor performance on complex data.
Optimizing option exercise policies based on variance optimal martingale measure can lead to unappealing results.
problem Optimizing American option exercise policies under the variance optimal martingale measure can result in unappealing policies.
method Optimizing option exercise policies under the variance optimal martingale measure, then anchoring to the resulting value of this policy.
result Optimizing option exercise policies based on the variance optimal martingale measure can lead to unappealing results.
Paper reviews synthetic data from AI models for statistical inference.
problem When can synthetic data be used reliably in statistical inference?
method Survey of generative models, statistical analysis of pitfalls.
result Principled use of synthetic data requires careful model specification.
Proposes a new undersampling method for imbalanced data classification.
problem Challenges of oversampling and undersampling in imbalanced data.
method Bilevel optimization framework for identifying optimal subset of majority training data.
result Improves F1 scores by up to 10% compared to state-of-the-art methods.
Statistical analysis reveals pitfalls in climate network construction.
problem Uncertainty in correlation estimates affects network characteristics.
method Simulated isotropic random fields and resampling procedures.
result Spurious link bundles and high-degree clusters are common.