Meta-analysis and systematic review can help distill machine learning research.
problem Difficulties in distilling a flood of machine learning papers into useful principles.
method Use meta-analysis and systematic review to aggregate and analyze machine learning research.
result Meta-analysis and systematic review can help in distilling machine learning research.
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.
Etalumis bridges scientific simulators and probabilistic programming.
problem Infeasibility of rewriting scientific simulators for Bayesian inference.
method Cross-platform probabilistic execution protocol, MCMC and IC engines, distributed training of 3DCNN-LSTM.
result Achieved largest-scale posterior inference in a Turing-complete PPL for LHC use-case.
Framework for interpreting ML models to reveal properties of real-world phenomena.
problem Lack of direct interpretability in modern ML models hinders scientific understanding.
method Developed 'property descriptors' grounded in statistical learning theory.
result Property descriptors can reveal relevant properties of joint probability distributions.
New algorithm for aggregate inference in HMMs with continuous observations.
problem Inference in large populations with indistinguishable individuals and continuous measurements.
method Continuous observation collective forward-backward algorithm extending existing discrete case algorithm.
result Efficacy demonstrated through numerical experiments.
A new method decouples set representation learning from posterior modeling for efficient amortized inference.
problem Efficient inference for large sets of observations with shared factors.
method Train a mean-pool Deep Set on sets of size at most two, then finetune the inference head on pre-aggregated embeddings.
result Matches or outperforms standard baselines at a fraction of the compute cost for large N.
SADA safely combines predictions from various models for semi-supervised learning.
problem Combining uncertain quality predictions from multiple models in semi-supervised learning.
method Safe and adaptive aggregation of black-box predictions.
result The method guarantees better performance than using labeled data alone and adapts to perfect predictions.
A new algorithm estimates aggregate marginals from noisy data in an online manner.
problem Estimating aggregate marginals of a Markov chain from noisy aggregate observations.
method Sliding window Sinkhorn belief propagation (SW-SBP) algorithm.
result Demonstrated improved performance on inferring population flow.
Proposes a method for stable variable selection in high-dimensional data.
problem Challenges of variable selection in high-dimensional, correlated data.
method Resample-aggregate framework using diffusion models.
result Stable subset of predictors with calibrated stability scores.
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.
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.
New method uses predictions to infer causal effects without labeled data.
problem Data labeling costs limit causal inference experiments.
method Prediction-Powered Causal Inferences (PPCI) using conditional calibration and transfer constraints.
result Valid causal inference achieved on experiments with no human annotations.
This paper provides a guide to feature importance methods for better scientific inference.
problem Limited understanding of data-generating process due to opaque ML model mechanisms.
method Comprehensive review and new proofs of global feature importance methods.
result Facilitates a thorough understanding and concrete recommendations for FI methods.
Proposes DCNAR for dynamic causal inference from neural time series.
problem Uncertainty and evolution of causal structure in real-world domains.
method Two-stage neural causal modeling integrating discovery and inference.
result Dynamic causal inferences are more stable and meaningful than alternatives.
Develops privacy-preserving methods for longitudinal linear regression.
problem Protecting individual information in longitudinal data with privacy-preserving statistics.
method Proposes a user-level private regression estimator and a privatized covariance estimator for longitudinal linear regression under user-level differential privacy.
result Establishes theoretical guarantees for practical user-level differential privacy estimation and inference in longitudinal linear regression.
FreB protocol uses AI to infer hidden parameters with valid confidence regions.
problem Generating biased or overconfident conclusions from AI-generated posterior distributions.
method Frequentist-Bayes (FreB) protocol reshapes AI-generated posterior distributions into valid confidence regions.
result FreB provides valid confidence regions that consistently include true parameters with expected probability.
Adaptive Bayesian learning aggregates experts to improve performance.
problem Bayesian online learning's performance depends on inferential choices.
method Treat Bayesian update rules as experts and aggregate them based on sequential predictive losses.
result The aggregate competes with the best expert in hindsight at a low aggregation cost.
New method for PINNs uncertainty quantification without prior distribution.
problem Lack of reliable uncertainty quantification for PINNs.
method Extended fiducial inference with narrow-neck hyper-network.
result Construction of honest confidence sets based on observed data.
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…
SVGP KAN integrates uncertainty quantification into Kolmogorov-Arnold networks.
problem Uncertainty quantification in scientific machine learning models.
method Sparse variational Gaussian process inference with Kolmogorov-Arnold topology.
result Demonstrated ability to distinguish aleatoric and epistemic uncertainty in various scientific applications.
SBI uses neural networks to infer model parameters from simulators.
problem Computational infeasibility of Bayesian inference for complex models.
method Training neural networks on simulator-generated data.
result Efficient Bayesian inference without likelihood evaluations.
Inference is the process of using facts we know to learn about facts we do not know. A theory of inference gives assumptions necessary to get from the former to the latter, along with a definition for and summary of the resulting uncertainty. Any one theory of inference is neither right nor wrong, but merely an axiom t…
New method produces coherent forecasts for long-range data.
problem Inaccurate and non-coherent forecasts on long-horizon data.
method Probabilistic forecasting with KL-divergence for coherent aggregates.
result Improves forecast performance across base levels and aggregates.
Federated learning leaks participant dataset quality even with secure aggregation.
problem Leakage of participant dataset quality in federated learning with secure aggregation.
method Image recognition experiments to infer and attribute dataset quality.
result Relative quality ordering of participants can be inferred and used for various purposes.
A new method calibrates scientific models by adding randomness to their predictions.
problem Current scientific foundation models lack calibrated uncertainty.
method Stochastic Attention, which randomizes attention weights using multinomial samples.
result Stochastic Attention achieves the strongest native calibration and sharpest prediction intervals.
Early-stopped aggregation improves computational efficiency in adaptive statistical inference.
problem Computational inefficiency in model selection and aggregation for adaptive inference.
method Early-stopped aggregation (ESA) framework: compute only a few simpler models using early-stopping criteria.
result ESA achieves optimal adaptive contraction rates in variational Bayes and frequentist settings.
Bayesian method learns from aggregated quantile data.
problem Limited access to sensitive personal data.
method Bayesian quantile matching estimation based on order statistics.
result Correctly reflects uncertainty of empirical quantiles.
Automates organizing diverse web data into a hierarchical topic model.
problem Manual classification of all scientific and popular scientific knowledge is impractical.
method Proposes an algorithm to aggregate multiple collections into a single hierarchical topic model.
result Demonstrates a web service for topical exploratory search.
SPACY discovers causal graphs from spatiotemporal data using variational inference.
problem Inferring causal relationships from high-dimensional spatiotemporal data with complex correlations.
method SPACY uses variational inference to model latent time series and their causal relationships, incorporating spatial factors to aggregate correlated data.
result SPACY outperforms state-of-the-art methods on synthetic and real-world data, identifying key causal phenomena.
Estimates proxy-based inference adjustments for distribution shifts.
problem Imperfect proxy data leads to biased inference.
method Empirical calibration of proxy-primary metric discrepancy as a random effect.
result Empowers inference without individual-level response data.
The paper clarifies conditions for using benchmark scores in machine learning.
problem Using benchmark scores to draw scientific inferences about learning problems.
method Developing conditions of construct validity inspired by psychological measurement theory.
result Clarifies conditions under which benchmark scores support diverse scientific claims.
Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.
problem Challenges in extracting meaningful peaks from noisy or complex spectra.
method Bayesian spectral deconvolution coupled with a physical-property regression layer.
result Recovery of weak peaks in poly(lactic acid) IR spectra related to degradation rates.
New algorithm for collective Gaussian hidden Markov models inference.
problem Inference of collective Gaussian hidden Markov models from aggregate data.
method Collective Gaussian forward-backward algorithm, extending Sinkhorn belief propagation.
result Convergence guarantee and applicability to single individual Kalman filter.
Develops EB for implicit likelihoods using simulators.
problem Traditional EB assumes tractable likelihoods, SBEB handles implicit likelihoods.
method Simulation-based empirical Bayes (SBEB) connects nonparametric EB to SBI, iteratively refining EB estimates.
result SBEB improves accuracy over SBI with fixed priors.
SVGP KAN integrates sparse variational GP with KANs for scalable probabilistic inference.
problem Lack of probabilistic outputs in standard KANs and cubic scaling of Gaussian Process methods.
method Sparse Variational GP-KAN combines KAN topology with sparse variational inference and permutation-based importance analysis.
result Enables probabilistic KANs to handle larger datasets with linear computational complexity.
SpaCE tackles spatial confounding in scientific studies.
problem Spatial confounding influences treatment and outcome, leading to spurious associations.
method Introduces SpaCE toolkit for benchmark datasets and tools to evaluate causal inference methods.
result Facilitates automated evaluation of machine learning and causal inference models.
New algorithm for efficient inference over tree-structured graphs.
problem Inference over probabilistic graphical models with aggregate data.
method Optimal transport theory, Sinkhorn/iterative scaling algorithm, belief propagation.
result Global convergence and polynomial computational complexity.
Unified ML imputation framework for missing data.
problem Invalid inference with incomplete data and ML imputations.
method Stratified by missingness patterns, weights and aggregates complete case information.
result Valid statistical inference for general missingness patterns.
ParaMonte simplifies Monte Carlo simulations for various scientific fields.
problem Efficiently performing Monte Carlo simulations for complex models.
method Unified, high-performance, parallelized library for C, C++, Fortran.
result Automates and streamlines Monte Carlo sampling for arbitrary-dimensional functions.
This paper tackles hidden state inference for HMMs using particle filtering.
problem Inference for hidden states under HMMs is challenging due to unavailable true labels.
method Adaptive conformal inference framework using particle filtering.
result The framework produces prediction sets with specific aggregated coverage levels.
HierarchicalForecast provides a Python framework for coherent hierarchical forecasting.
problem Ensuring forecasts at disaggregate levels add up to aggregate forecasts.
method Preprocessed datasets, evaluation metrics, and statistical baseline models.
result Python-based reference framework for statistical and ML forecasting.
Model infers functions for attributes using multi-aggregate datasets with knowledge transfer.
problem Modeling aggregate data with varying granularities and spatial supports.
method Multi-output Gaussian process (MoGP) with linear mixing of independent latent GPs, aggregation process, and prior distribution of mixing weights.
result Proposed model outperforms in refining coarse-grained aggregate data.
AKO improves stability and power of Knockoff inference.
problem Instability of Knockoff-based inference.
method Aggregation of Multiple Knockoffs (AKO) method.
result AKO maintains FDR control while improving stability and power.
FedBE aggregates local models into a robust global model via Bayesian inference.
problem Challenges in aggregating non-i.i.d. local models into a global model in federated learning.
method FedBE uses Bayesian inference to sample and combine higher-quality global models from local models.
result FedBE leads to more robust aggregation of local models into a global model, especially when data is non-i.i.d.
TopicEq model generates equations and text from scientific papers.
problem Communicating ideas in scientific texts using both mathematics and text.
method Joint topic and equation generation model using correlated topic model and RNN.
result Joint model outperforms existing topic and equation models for scientific texts.
Celeste is a procedure for inferring astronomical catalogs that attains state-of-the-art scientific results. To date, Celeste has been scaled to at most hundreds of megabytes of astronomical images: Bayesian posterior inference is notoriously demanding computationally. In this paper, we report on a scalable, parallel v…
Paper studies estimating network properties with missing data using SRL and GNN.
problem Estimating aggregate properties in networks with missing data attributes.
method Comparative study of SRL and GNN approaches for inferring missing attributes and estimating aggregate properties.
result SRL-based approaches tend to outperform GNN-based approaches in estimating aggregate properties and predictive accuracy.
Paper presents a framework to infer individual data from aggregate data.
problem Inference of individual-level data from aggregate data due to privacy concerns.
method End-to-end pipeline for processing aggregate data, novel algorithm for reconstruction, machine learning models.
result Valid and usable answers derived from machine learning models using multiple candidate datasets.