LLMs fail to match statistical ground truth despite stable run-to-run performance.
problem LLMs lack validation against statistical ground truth in automated scientific workflows.
method Introduced a behavioral evaluation framework for LLMs, separating four decision-making dimensions.
result LLMs can exhibit near-perfect stability but diverge from statistical ground truth.
iKF method uncovers complex variable interactions for scientific discovery.
problem Limited interpretability of existing models in decision-making applications.
method Iterative Kings' Forests (iKF) method to uncover multi-order interactions.
result iKF provides strong interpretive power for explainable modeling.
A textbook on machine learning explaining patterns, predictions, and actions.
problem Understanding patterns in data for predictions and actions.
method Explains foundations of decision making, representation, optimization, and generalization.
result Equips readers with tools to reason about actions and their consequences.
Clarifies the various fairness definitions in ML.
problem Addressing fairness in ML with different definitions.
method Analyzes and clarifies the differences between fairness definitions.
result Provides a clearer understanding of fairness definitions in ML.
Modeling decision-making dynamics in MDD patients using RL-HMM.
problem Characterize reward learning strategies in MDD patients.
method Proposed RL-HMM framework to analyze reward-based decision-making.
result MDD patients show reduced engagement in RL compared to healthy controls.
Paper introduces MTGP for engineering tasks with sparse data.
problem Challenges of data sparsity and varying task correlations in engineering.
method Multi-Task Gaussian Processes (MTGP) framework.
result Improves predictive performance and reduces computational costs.
Linguistic calibration improves long-form text confidence.
problem LMs hallucinate, leading to suboptimal decisions.
method Defining linguistic calibration, training framework, reinforcement learning.
result Llama 2 7B is significantly more calibrated than baselines.
NEON uses neural networks to optimize functions in infinite-dimensional spaces.
problem Optimizing composite functions in function spaces.
method NEON (Neural Epistemic Operator Networks) for sequential decision-making.
result NEON achieves state-of-the-art performance with fewer parameters.
This guide explains statistical distances for evaluating generative models.
problem Evaluating the quality of samples from generative models.
method Four statistical distances: SW, C2ST, MMD, FID.
result Different distances can yield varying results on similar data.
Survey connects XAI and surrogate modeling for better understanding of complex systems.
problem Opaque surrogate models hide input-output relationships, hindering decision-making.
method Synthesizes XAI techniques with surrogate modeling workflows.
result Surrogate models can be made more interpretable using XAI methods.
Optimization is becoming increasingly common in scientific and engineering domains. Oftentimes, these problems involve various levels of stochasticity or uncertainty in generating proposed solutions. Therefore, optimization in these scenarios must consider this stochasticity to properly guide the design of future exper…
The paper aims to improve reproducibility of machine learning experiments.
problem Lack of reproducibility in machine learning experiments.
method Investigates factors affecting reproducibility and proposes FAIR data practices.
result Preliminary results show the role of ProvBook in capturing and comparing provenance.
FOCaL meta-learner estimates functional treatment effects robustly.
problem Estimating heterogeneous treatment effects from functional outcomes.
method Doubly robust meta-learner FOCaL integrating functional regression.
result Direct and robust estimation of F-CATE.
xVal tokenizes numbers continuously for better scientific model training.
problem Lack of continuous numerical tokenization for scientific datasets in LLMs.
method xVal: Continuous numerical tokenization strategy.
result xVal outperforms other numerical tokenization methods on scientific datasets.
Galactica learns from scientific literature to help researchers.
problem Information overload in scientific literature makes it hard to find useful insights.
method Trained on a large corpus of scientific papers, reference material, and knowledge bases.
result Outperforms existing models on various scientific tasks, including LaTeX equations and mathematical reasoning.
Behavioral Finance has become a challenge to the scientific community. Based on the assumption that behavioral aspects of investors may explain some features of the Stock Market, we propose an agent based model to study quantitatively this relationship. In order to approximate the simulated market to the complexity of …
Data science models, although successful in a number of commercial domains, have had limited applicability in scientific problems involving complex physical phenomena. Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of da…
Social media enhances or diminishes scientific status, depending on usage.
problem Impact of social media on scientific stratification and mobility.
method Logistic Attribution Analysis combining statistical and machine learning methods.
result Social media promotes stratification and mobility, but beyond a threshold, it negatively impacts status.
Evidence shows that in a significant number of cases the current methods of research do not allow for reproducible and falsifiable procedures of scientific investigation. As a consequence, the majority of critical decisions at all levels, from personal investment choices to overreaching global policies, rely on some va…
There is significant interest in using modern neural networks for scientific applications due to their effectiveness in modeling highly complex, non-linear problems in a data-driven fashion. However, a common challenge is to verify the scientific plausibility or validity of outputs predicted by a neural network. This w…
Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.
problem Estimating unknown parameters in hybrid models combining machine learning and scientific models.
method Sharpness-aware minimization adapted for hybrid modeling, focusing on model simplicity.
result Demonstrates effectiveness of SAM-based hybrid model learning for scientific parameter estimation.
AutoSciDACT detects scientific anomalies in noisy data.
problem Detecting anomalies in large, noisy scientific datasets.
method Contrastive pre-training for low-dimensional data representations, two-sample test using NPLM.
result Strong sensitivity to small anomalies across various scientific domains.
MDNs offer a data-efficient alternative to diffusion and flow models for multimodal scientific learning.
problem Capturing multimodal conditional uncertainty in scientific inverse problems.
method Mixture Density Networks (MDNs) as explicit parametric density estimators.
result MDNs achieve superior generalization, interpretability, and sample efficiency in scientific tasks.
New framework assesses extreme errors in machine learning models.
problem Current validation methods fail to quantify extreme errors in high-stakes domains.
method Uses Extreme Value Theory (EVT) to estimate worst-case failures.
result Establishes EVT as a fundamental tool for assessing model reliability.
Optimizes investment model using LSTM for better risk control.
problem Enhancing risk control in multi-factor investment models.
method Combines LSTM with multi-factor investment model for factor selection and weight determination.
result LSTM model outperforms benchmark in risk control metrics.
Survey of deep learning models for scientific discovery.
problem Identifying which scientific problems are most suitable for deep learning.
method Overview of deep learning models, tasks, training methods, and techniques.
result Helps accelerate deep learning use in scientific domains.
New framework compresses and recovers scientific data efficiently.
problem Efficiently managing and recovering from large scientific datasets.
method Grounded in learning exponential families, preserves uncertainty and supports trade-offs.
result Preserves physical features and quantities of interest in compressed representations.
Hurd's career overview and publications listed.
problem None explicitly stated in the abstract.
method Not applicable as it's an introduction.
result No specific key result mentioned.
This thesis advances algorithms and software for QMC, GP, and sciML.
problem Efficient high-dimensional integration, interpolation, and PDE modeling.
method Developed new algorithms and software for QMC, GP, and sciML.
result Efficient and accurate methods for high-dimensional problems.
New AI approach improves quantum device calibration by leveraging prior scientific discoveries.
problem Lack of abundant data in scientific disciplines hinders model generalizability.
method Introduces a new machine learning approach that combines prior scientific knowledge with data.
result Accuracy in predicting quantum device energy spectrum surpasses current state-of-the-art by over 20%.
Before retiring, looking back to forty years of writing and publishing scientific papers, I decided to present to the scientific community a selection of my scientific works. I chose mostly articles published in prestigious journals or Proceedings that made a certain impact in the scientific world. I have selected thir…
Why do nations produce scientific research? This is a fundamental problem in the field of social studies of science. The paper confronts this question here by showing vital determinants of science to explain the sources of social power and wealth creation by nations. Firstly, this study suggests a new general definitio…
Figures are an important channel for scientific communication, used to express complex ideas, models and data in ways that words cannot. However, this visual information is mostly ignored in analyses of the scientific literature. In this paper, we demonstrate the utility of using scientific figures as markers of knowle…
Algorithm identifies interpretable subgroups with elevated treatment effects.
problem Estimating high-dimensional, uninterpretable CATE results.
method Rule sets summarizing CATE estimates, optimizing subgroup size and effect size.
result Frontier of Pareto optimal rule sets for subgroup identification.
Develops significance tests for neural networks without strong assumptions or excessive computation.
problem Addressing the black-box nature of deep neural networks for feature relevance testing.
method Derives one-split and two-split tests relaxing assumptions and computational complexity.
result Establishes asymptotic null distributions and consistency in Type II error.
Proposes SHORE model for efficient MOR with sparsity and scalability.
problem Challenges of interpretability and scalability in MOR with high-dimensional outputs.
method Incorporates sparsity requirements and a two-stage optimization framework for efficient compression.
result Theoretical and empirical validation of the proposed framework's efficiency and accuracy.
Paper presents a workflow for reliable unsupervised learning in science.
problem Lack of standardization in unsupervised learning workflows for reproducible scientific discoveries.
method Structured workflow including data preparation, modeling, validation, and communication.
result Illustrates the importance of validation in unsupervised learning.
Develops a Bayesian framework for symbolic regression of scientific expressions.
problem Lack of principled uncertainty quantification and interpretability in existing symbolic regression methods.
method Hierarchical Bayesian framework with tree-structured symbolic expressions and Markov chain Monte Carlo inference.
result Robust performance on various datasets, including single-atom catalysis.
Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and di…
EduQG generates better educational questions by pre-training on scientific text.
problem Improving the quality of educational questions for scalable self-assessment.
method Adapting a large language model for educational question generation, pre-trained on scientific text.
result EduQG produces superior educational questions compared to baseline models.
SOS-VAE improves generative models for scientific applications by correcting decoder bias.
problem Bias in generative parameters due to supervised learning in VAEs.
method Develops SOS-VAE framework to influence decoder for predictive latent representation.
result Ensures reliable generative parameters for scientific applications.
GPR enhances materials discovery by automating parameter space exploration.
problem Automating exploration of large, high-dimensional parameter spaces in materials science.
method Gaussian process regression with inhomogeneous measurement noise and anisotropic kernels.
result Importance and benefits of tuning GPR for materials science experiments.
RAMPART ranks top-k features more accurately than existing methods.
problem Accurate ranking of important features in machine learning.
method Adaptive sequential halving strategy combined with ensembling techniques.
result RAMPART achieves the correct top-k ranking with high probability.
Economics does not need a scientific revolution. Economics needs accurate measurements according to high standards of natural sciences and meticulous work on revealing empirical relationships between measured variables.
Differentiable programming aids in solving differential equations and their sensitivities.
problem Computing gradients of numerical solutions of differential equations.
method Review of existing techniques and mathematical foundations.
result Established a coherent framework for combining differential equations with data-driven approaches.
Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthet…
Scientific documents rely on both mathematics and text to communicate ideas. Inspired by the topical correspondence between mathematical equations and word contexts observed in scientific texts, we propose a novel topic model that jointly generates mathematical equations and their surrounding text (TopicEq). Using an e…
PIMA autoencoders discover shared features in multimodal scientific data.
problem Discovering shared information in high-throughput scientific datasets.
method Physics-informed multimodal autoencoders (PIMA) with Gaussian mixture prior and product of experts formulation.
result Accurate cross-modal inference between images and mechanical stress-strain response in lattice metamaterials.