Automatically computes reference ranges for UK Biobank cardiac data.
problem Improving healthcare by discovering patterns in large-scale population data.
method Fully automatic pipeline for 3D cardiac MR image analysis.
result Statistically significant agreement between manual and automatic indexes.
Study finds phase transition in context-sensitive language model with short-range interactions.
problem Understanding phase transitions in language models with short-range interactions.
method Constructed a random language model with short-range interactions and investigated its statistical properties.
result Phase transition occurs in context-sensitive language models with constant context length.
Uniswap markets perform well and closely track reference prices.
problem Understanding and validating the performance of Uniswap markets.
method Formal analysis and numerical simulation of constant product markets.
result Uniswap markets closely track reference prices under common conditions.
This paper solves the multiple reference model problem in RLHF with exact solutions and sample complexity guarantees.
problem Limitations of single reference models in aligning LLMs with human feedback.
method Integrates multiple reference models into RLHF frameworks, addressing theoretical challenges with exact solutions and sample complexity guarantees.
result First exact solution to the multiple reference model problem in reverse KL-regularized RLHF.
Leveraging reference-only samples for two-sample testing under size asymmetry
problem Two-sample testing under size imbalance
method Adaptive aggregation of reference-dependent representations
result Strong performance with type I error control
Range penalization enhances statistical accuracy and resource efficiency in federated learning.
problem Statistical accuracy and resource efficiency in federated learning.
method Range regularization and polar clustering.
result Enhanced statistical accuracy and reduced iteration complexity.
This paper improves indoor positioning accuracy by deploying reference nodes to ensure Line-of-Sight.
problem Systematic bias errors in indoor positioning due to non-LoS propagation.
method Model indoor service area as a graph, partition into cliques for reference nodes, set minimum distance and angle parameters.
result Guaranteed LoS to reference nodes improves indoor positioning accuracy and precision.
NegToMe uses images to guide text-based models away from unwanted visual elements.
problem Insufficient text-based adversarial guidance for complex visual concepts.
method Negative token merging (NegToMe) using visual features from reference images.
result Significantly enhances output diversity and reduces visual similarity to copyrighted content.
Paper proposes using LSTM for LSH-based sequence alignment.
problem Sequence alignment using deep learning models.
method Deep bidirectional LSTM for feature learning and LSH-based sequence alignment.
result Higher accuracy achieved with LSTM-based model.
Multi-instance learning (MIL) has a wide range of applications due to its distinctive characteristics. Although many state-of-the-art algorithms have achieved decent performances, a plurality of existing methods solve the problem only in instance level rather than excavating relations among bags. In this paper, we prop…
A heuristic method for determining input ranges for complex processes.
problem Determining input variable ranges for non-numeric, high-dimensional processes.
method Create synthetic training data and use a decision tree classifier.
result Validated on a real use case in a lamination factory.
MambaLRP enhances Mamba models' explainability and performance.
problem Lack of transparency in Mamba models for real-world applications.
method Layer-wise Relevance Propagation (LRP) with relevance conservation axioms.
result MambaLRP provides stable and reliable explanations for Mamba models.
The distribution of wealth among the members of a society is herein assumed to result from two fundamental mechanisms, trade and investment. An empirical distribution of wealth shows an abrupt change between the low-medium range, that may be fitted by a non-monotonic function with an exponential-like tail such as a Gam…
Sparse learning has been shown to be effective in solving many real-world problems. Finding sparse representations is a fundamentally important topic in many fields of science including signal processing, computer vision, genome study and medical imaging. One important issue in applying sparse representation is to find…
Neural models use default reasoning for number and gender assignment tasks.
problem Understanding how neural language models make decisions for grammatical phenomena.
method Generalised Contextual Decomposition (GCD) to isolate semantic, syntactic, and bias-driven components of predictions.
result Models rely on default reasoning for tasks like number and gender assignment.
Estimates LRD in sequential data, improving RNNs.
problem Quantifying LRD in sequential data for better RNNs.
method Principled estimation procedure based on LRD theory for real-valued time series.
result Estimates LRD reliably in user behavior and Wikipedia article writing.
Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only while training, but also when deployed at scales ranging from data centers all th…
This paper calculates worst-case VaR for financial markets using empirical data and model uncertainty.
problem Quantifying risk under model uncertainty for financial risk management.
method Proposed a two-layer mixed distribution model to simplify model uncertainty, used change point detection and EM algorithm for estimation.
result Calculated VaR, WVaR, and BVaR for four financial markets, analyzed their performance.
Paper optimizes liquidity provision in decentralized finance markets.
problem Strategic LPs face predictable losses and concentration risk in CL pools.
method Derive optimal liquidity provision strategy based on fees, PL, and concentration risk.
result Optimal strategy increases fee revenue and profit from marginal rate changes.
Paper quantifies distortion risk measures' robustness to distributional uncertainty.
problem Quantifying risk measures' robustness to distributional uncertainty.
method Employing isotonic projections, the paper derives bounds on distortion risk measures' values.
result Sharp bounds on distortion risk measures' values are provided, especially for Value-at-Risk and Range-Value-at-Risk.
Automated method bounds causal effects in discrete data.
problem Partial identification of causal effects in discrete settings.
method Polynomial programming and dual relaxation for automated bounds.
result Algorithm provides guaranteed non-sharp and ε-sharp bounds. Committee neural network models improve accuracy and enable active learning for interatomic potentials.
problem Improving accuracy and generalization error in interatomic potentials.
method Adapting committee models to neural networks, using multiple models with shared descriptors, and applying active learning to select configurations.
result Committee disagreement provides a measure of generalization error and guides active learning to minimize it.
Embedded ensembles improve neural network performance efficiently.
problem Improving neural network performance with fewer resources.
method Analyzing the wide network limit of gradient descent dynamics using Neural-Tangent-Kernel.
result Embedded ensembles exhibit two regimes: independent and collective, affecting performance.
Differential Evolution outperforms SMAC in hyperparameter tuning.
problem Automated hyperparameter tuning for machine learning.
method Empirical study comparing Differential Evolution to SMAC.
result Differential Evolution outperforms SMAC on most datasets.
TMSCD detects multi-scale communities in temporal networks automatically.
problem Discovering multi-scale communities in large, evolving networks.
method Spectral multilayer formulation of MM method with automatic parameter selection.
result Automatic detection of multi-scale communities without manual parameter selection.
MACE architecture outperforms alternatives in various molecular and materials science tasks.
problem Improving machine learning force fields for diverse molecular and materials science applications.
method Evaluation of MACE architecture on various datasets and tasks, demonstrating data efficiency and excellent performance.
result MACE architecture generally outperforms alternatives across a wide range of systems, including amorphous carbon, universal materials modelling, and organic chemistry.
The paper proposes a new approach to model risk measurement based on the Wasserstein distance between two probability measures. It formulates the theoretical motivation resulting from the interpretation of fictitious adversary of robust risk management. The proposed approach accounts for equivalent and non-equivalent p…
New risk factors improve stress testing accuracy.
problem Improving stress testing accuracy with new risk factors.
method Adapted PCA and autoencoders for dimension reduction and interpretation.
result Aggregated risk factors enhance stress testing outcomes.
Geometric methods solve sampling, optimisation, inference, and adaptive decision-making.
problem Efficient solutions for sampling, optimisation, inference, and adaptive decision-making.
method Derive algorithms exploiting geometric structures of Hamiltonian systems, Hilbertian subspaces, and information geometry.
result Wide range of geometric theories emerge in these fields, enabling efficient solutions.
Distance between evolving hypersurfaces is a PDE solution.
problem Tracking the distance between evolving hypersurfaces.
method Elliptic and parabolic PDEs, mean curvature flow.
result Local Harnack inequalities for the distance between evolving hypersurfaces.
Unified theory explains diversity in ensemble learning.
problem Explaining diversity in ensemble learning across various scenarios.
method Developed a framework revealing diversity as a hidden dimension in bias-variance decomposition.
result Proved exact bias-variance-diversity decompositions for multiple losses in regression and classification.
Efficiently finds diverse coherent counterfactual explanations.
problem Finding coherent counterfactual explanations for complex data.
method Mixed integer programming with mixed polytope constraints.
result Efficiently generates diverse coherent counterfactual explanations.
Inferring the laws of interaction between particles and agents in complex dynamical systems from observational data is a fundamental challenge in a wide variety of disciplines. We propose a non-parametric statistical learning approach to estimate the governing laws of distance-based interactions, with no reference or a…
Unified access package for fundamental physics datasets simplifies machine learning.
problem Lack of unified access to datasets from multiple fundamental physics disciplines.
method Unified Python package with common interface and reference models.
result Graph-based neural networks perform similarly to dedicated methods on various datasets.
In this paper, we develop a Bayesian evidence maximization framework to solve the sparse non-negative least squares (S-NNLS) problem. We introduce a family of probability densities referred to as the Rectified Gaussian Scale Mixture (R- GSM) to model the sparsity enforcing prior distribution for the solution. The R-GSM…
We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree models (HLTMs). The variables at the bottom level of an HLTM are observed binary va…
This article reviews forecasting theory and practice.
problem Forecasting uncertainty and challenges in decision making.
method Overview of forecasting models, principles, and applications.
result Encyclopedic presentation of forecasting theory and practice.
New methods improve LLM preference optimization by intelligently weighting multiple reference models.
problem Improving LLM preference optimization with multiple reference models.
method Introducing four new weighting strategies for multiple-reference preference optimization.
result All four new weighting strategies outperform current methods on preference accuracy.
An important problem in geostatistics is to build models of the subsurface of the Earth given physical measurements at sparse spatial locations. Typically, this is done using spatial interpolation methods or by reproducing patterns from a reference image. However, these algorithms fail to produce realistic patterns and…
Time-series calibrations often suggest that the GARCH diffusion model could also be a suitable candidate for option (risk-neutral) calibration. But unlike the popular Heston model, it lacks a fast, semi-analytic solution for the pricing of vanilla options, perhaps the main reason why it is not used in this way. In this…
Study compares FDA and ML methods for time series classification.
problem Comparing functional data analysis and machine learning for time series classification.
method Functional generalized additive models, feature extraction, basis representations, support vector machines, classification trees.
result Benchmarking and ranking of methods for non-expert practitioners.
Unified evaluation framework for sampling methods.
problem Lack of a standardized evaluation framework for sampling methods.
method Introduces a benchmark suite and performance criteria for sampling methods.
result Insights into strengths and weaknesses of existing sampling methods.
The paper examines rigidity in geometric actions of Coxeter groups on Croke-Kleiner spaces.
problem The rigidity of geometric actions of Coxeter groups compared to their quasi-isometric counterparts.
method Study of right-angled Coxeter groups acting geometrically on Croke-Kleiner spaces.
result Right-angled Coxeter groups have more rigid geometric actions than their quasi-isometric counterparts.
Techniques known as Nonlinear Set Membership prediction, Lipschitz Interpolation or Kinky Inference are approaches to machine learning that utilise presupposed Lipschitz properties to compute inferences over unobserved function values. Provided a bound on the true best Lipschitz constant of the target function is known…
Optimal transport embedding learns feature sets efficiently.
problem Learning on sets of features with long-range dependencies and few labeled data.
method Parametrized fixed-size embedding that aggregates features according to optimal transport plan.
result Achieves state-of-the-art results on protein fold recognition and chromatin profiles.
COCA accelerates N-body simulations by correcting ML errors.
problem Computational expense and limited trustworthiness of ML emulations.
method Hybrid framework combining ML and N-body simulator in an emulated frame of reference. result COCA reduces emulation errors with fewer force evaluations.
Paper generalizes tensor-train approximation for complex random variables.
problem Characterizing intractable high-dimensional random variables.
method Extends inverse Rosenblatt transform to general reference measures and integrates into deep variable transformation framework.
result Deep inverse Rosenblatt transport significantly expands tensor approximations for complex random variables.
This paper uses reference priors to improve deep learning models with unlabeled and labeled data.
problem Improving deep learning models with limited labeled data and unlabeled data from the same or related tasks.
method Develops and applies generalizations of reference priors for deep networks to exploit unlabeled and labeled data.
result Demonstrates new semi-supervised learning and pretraining methods for transfer learning.