The paper optimizes private data sharing by selecting statistics and using MCMC for Bayesian inference.
problem Optimizing private data sharing by selecting statistics and performing Bayesian inference.
method Promotes Fisher information for statistic selection and proposes MCMC algorithms for inference.
result The Fisher information of the privatized statistic predicts the relative performance of the statistic in Bayesian estimation.
New bounds on learning shared representations improve model performance and efficiency.
problem Improving model performance and efficiency through shared representations across clients.
method Established new upper and lower bounds on statistical error, designed a spectral estimator for non-convex least-squares solutions.
result Optimal statistical rate achieved when shared representation is well covered across clients.
New test assesses shared brain activity across different cognitive modalities.
problem Determining if different cognitive modalities use overlapping neural representations.
method Formulated a statistical hypothesis testing approach using permutation testing.
result New test (CMPT) has greater statistical power than cross-modal decoding while maintaining low Type I errors.
The paper shows how shared random seeds can reduce variance in machine learning evaluations.
problem The statistical structure of comparative evaluation under shared random seeds is not well understood.
method An extended learning-based multi-agent economic simulator was used to demonstrate the effects of shared random seeds on variance reduction.
result Pairing seeds can reduce variance in machine learning evaluations, especially when outcomes are positively correlated at the seed level.
Surveying joint Gaussian graphical models to identify shared structures across domains.
problem Estimating shared structures across different data sources.
method Statistical inference of joint Gaussian graphical models.
result Improved estimation power for high-dimensional data.
A framework isolates and learns approximately shared features for better domain adaptation.
problem Reducing performance degradation in unseen domains using machine learning models.
method Statistical framework distinguishing feature utilities based on correlation variance across domains. Learning approximately shared features from source tasks and fine-tuning on target tasks.
result Improved population risk compared to previous results on both source and target tasks, resolving the paradox of feature selection.
Near-optimal rates for multi-task learning with shared representations.
problem Approximation and statistical complexity of learning multiple operators.
method Multiple Neural Operators (MNO) architecture and comparison with DeepONet.
result Near-optimal upper and lower bounds for approximation and generalization.
Much recent machine learning research has been directed towards leveraging shared statistics among labels, instances and data views, commonly referred to as multi-label, multi-instance and multi-view learning. The underlying premises are that there exist correlations among input parts and among output targets, and the …
DeepSeekMoE improves language model efficiency with shared experts and normalized gating.
problem Improving sample efficiency in language model architectures.
method Theoretical and empirical analysis of shared experts and normalized sigmoid gating.
result Theoretical and empirical evidence of improved sample efficiency with shared experts and normalized gating.
The study examines how weight sharing, equivariance, and locality affect the sample complexity of neural networks.
problem Understanding the impact of design choices on the generalization error of neural networks.
method Statistical learning theory applied to single hidden layer networks with weight sharing, equivariance, and locality.
result Lower and upper bounds for sample complexity are derived, showing that locality has benefits but comes with a trade-off.
This chapter reviews statistical tools for reinforcement learning.
problem Applying RL algorithms in healthcare and ride-sharing platforms.
method Statistical inference tools for RL, including hypothesis testing and confidence interval construction.
result Highlighting the value of statistical inference in RL for both communities.
A novel Bayesian framework for private linear regression with MCMC.
problem Private linear regression in a distributed setting.
method Generative statistical model, MCMC algorithms, fast Bayesian estimation.
result The proposed methods provide well-rounded estimation and prediction.
We statistically investigate the distribution of share price and the distributions of three common financial indicators using data from approximately 8,000 companies publicly listed worldwide for the period 2004-2013. We find that the distribution of share price follows Zipf's law; that is, it can be approximated by a …
Multi-model forgetting occurs when training multiple deep networks sequentially, leading to performance degradation of previously trained models.
problem Performance degradation of previously trained models when sequentially training multiple deep networks with shared parameters.
method Introduce a weight plasticity loss that regularizes the learning of shared parameters based on their importance for previous models.
result Weight plasticity loss effectively preserves the performance of previously trained models during sequential training and neural architecture search.
Method embeds numeric tabular datasets into a shared vector space for similarity and retrieval.
problem Lack of meaningful representation for numeric tabular datasets in large language models.
method Structured exploratory data analysis descriptors, sentence transformer embedding, CCA for cross-dataset alignment.
result Total P@1 score of 0.9 across 15 datasets, robust nearest-neighbor retrieval and cluster structure.
CNNs require fewer samples than LCNs and FCNs for image-based tasks due to locality and weight sharing.
problem Quantifying statistical benefits of locality and weight sharing in CNNs over LCNs and FCNs.
method Dynamic Signal Distribution (DSD) task and information theoretic tools.
result CNNs require fewer samples than LCNs and FCNs for image-based tasks.
Model improves covariance estimation from shared and distinct datasets.
problem Limited sample sizes and shared covariance structure across related datasets.
method Spiked covariance model with shared subspace, closed-form pooling weight, and asymptotic guarantees.
result Improves estimation of high-dimensional covariance matrices from related datasets.
We introduce a new statistical test of the hypothesis that a balanced panel of firms have the same growth rate distribution or, more generally, that they share the same functional form of growth rate distribution. We applied the test to European Union and US publicly quoted manufacturing firms data, considering functio…
Survey of robust streaming techniques and their relationships.
problem Challenges in robust streaming and online learning.
method Overview and survey of robust streaming techniques, unifying theorems.
result Proved the relationship between robust streaming techniques.
Develops S-EFE for analyzing grouped data, improving word usage interpretation.
problem Analyzing how words are used differently across related groups of data.
method Structured exponential family embeddings (S-EFE) with hierarchical modeling and amortization.
result S-EFE enables group-specific interpretation of word usage and outperforms EFE.
New statistical manifolds derived from identity map biharmonicity.
problem Deriving new statistical manifolds from identity map biharmonicity.
method Statistical biharmonicity of identity maps, semi-equiaffine condition, constant curvature.
result Determined statistical structures of new class of manifolds.
This paper surveys techniques to personalize federated learning models.
problem Personalized models outperform shared models for some clients, reducing participation.
method Surveys recent research on personalizing federated learning models.
result Personalization techniques improve model performance for individual clients.
CEDAR efficiently analyzes distributed EHR data without sharing patient-level info.
problem Analyzing patient-level data from multiple EHRs databases without sharing raw data.
method Tackles by turning problem into missing data, incorporating posterior samples.
result Improves efficiency and privacy of parameter estimates in sparse regressions.
Novel framework detects lead-lag relationships in Chinese A-share market.
problem Detecting lead-lag relationships in the Chinese A-share market.
method Two-stage framework: long-term coupling via correlation, dynamic time warping, and rank-based metrics; high-frequency data analysis via cross-correlation, Granger causality, and regression models.
result Strongly coupled stock pairs often exhibit lead-lag effects, especially at finer time scales.
The paper addresses risk sharing and variability measures among agents with general risk preferences.
problem Risk sharing and variability measures among agents with general risk preferences.
method Characterizes Pareto-optimal allocations using Gini deviation, mean-median deviation, and inter-quantile difference as variability measures.
result Optimal allocations are not comonotonic and feature a mixture of pairwise counter-monotonic structures.
New model transforms mixed data into homogeneous representation.
problem Handling heterogeneous mixed data with minimal loss of information.
method Parameter sharing and balancing extensions to MV.RBM, structured sparsity, and distance metric learning.
result Models perform better than baseline methods in medical data and outperform state-of-the-art rivals in image datasets.
Bayesian model transfers knowledge across different engineering fleets.
problem Data sparsity in predictive models for engineering infrastructure.
method Hierarchical Bayesian approach with multitask learning.
result Improves survival analysis and power prediction in truck fleets and wind farms.
FLUID uses flows to unify filtering and smoothing for complex systems.
problem Bayesian filtering and smoothing for high-dimensional nonlinear systems.
method FLUID encodes observation histories into a fixed summary statistic, using flows for filtering and smoothing.
result FLUID provides accurate approximations of filtering and smoothing distributions.
Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training examples may share some common objects, and hence share the features of these shared objects. We …
Estimates multiple connected linear regressions with refined common and individual parameters.
problem Multi-task learning in high-dimensional settings.
method Introduced an estimator for multiple connected linear regressions with refined common and individual parameters.
result Proposed an iterative estimation algorithm with geometric convergence rate and provided a high probability non-asymptotic bound for estimation error.
Decentralized detection avoids sharing data, controls false discoveries.
problem Global false discovery rate control in decentralized novelty detection.
method Quantized surrogate models for low-precision sharing, preserving exchangeability.
result Quantized composite scores maintain competitive statistical power with reduced communication.
New statistical guarantees for transfer learning with diverse tasks.
problem Statistical guarantees for transfer learning across different tasks.
method Formal analysis of t+1 tasks with shared representation. result Sample complexity reduction for new tasks using shared representation.
Diffusion models adapt to low-dimensional structures for nonparametric density estimation.
problem High-dimensional statistical inference challenges.
method Viewing diffusion models as implicit density estimators and exploiting their low-dimensional structure.
result Achieves minimax optimal rate for total variation distance with factorizable density.
A new method is proposed to obtain the risk neutral probability of share prices without stochastic calculus and price modeling, via an embedding of the price return modeling problem in Le Cam's statistical experiments framework. Strategies-probabilities Pt0,n and PT,n are thus determined and used, respective…
DAF uses attention sharing to adapt forecasts from abundant to scarce data.
problem Limited data for time series forecasting.
method Attention-based shared module and domain discriminator for domain adaptation.
result DAF outperforms state-of-the-art methods on various domains.
The symbolic dynamics technique is well-known for low-dimensional dynamical systems and chaotic maps, and lies at the roots of the thermodynamic formalism of dynamical systems. Here we show that this technique can also be successfully applied to time series generated by complex systems of much higher dimensionality. Ou…
PRISM-FCP improves federated prediction robustness against Byzantine attacks.
problem Byzantine attacks in federated learning.
method Partial model sharing and distance-based maliciousness scores.
result Maintains nominal coverage guarantees under Byzantine attacks.
BIDIFAC integrates multi-platform, multi-cohort data for shared and unique patterns.
problem Integration of multi-platform, multi-cohort data for shared and unique patterns.
method BIDIFAC integrates bidimensionally linked matrices into four components: globally shared, row-shared, column-shared, and single-matrix structural components.
result BIDIFAC reveals shared and unique patterns of variability in multi-platform, multi-cohort data.
FedLog reduces communication in federated learning by sharing data summaries.
problem Significant communication overhead in federated learning with large model parameters.
method Shares minimal sufficient statistics via Bayesian inference and differential privacy.
result High learning accuracy with low communication overhead.
Simple bounds show most cross-sectional predictability findings are likely true.
problem Determining the validity of cross-sectional return predictability findings.
method Developed simple and intuitive bounds on the false discovery rate (FDR).
result Bounds show the FDR is small, indicating most findings are likely true.
Deep neural networks and glassy systems share dynamics but differ in landscape properties.
problem Comparing training dynamics of DNNs and glassy systems.
method Statistical physics methods applied to DNN training.
result DNN dynamics slow down due to many flat directions, diffusing at the loss minimum.
DFI maps covariates to latent representations for feature importance.
problem Feature importance when predictors are statistically dependent.
method Disentangled Feature Importance (DFI) using entropic optimal transport.
result DFI yields stable, interpretable, uncertainty-quantified attributions of shared predictive signal.
A competing market model with a polyvariant profit function that assumes "zeitnot" stock behavior of clients is formulated within the banking portfolio medium and then analyzed from the perspective of devising optimal strategies. An associated Markov process method for finding an optimal choice strategy for monovariant…
CoreFlow models matrix-valued distributions efficiently, preserving shared low-rank structure.
problem Learning matrix-valued distributions from high-dimensional and incomplete data.
method Low-rank flow model that learns shared row/column subspaces and trains a normalizing flow on the core.
result CoreFlow improves generation quality in few-sample regimes and remains competitive in data-rich settings.
New test ensures quality of shared data in machine learning.
problem Ensuring quality of external data in machine learning tasks.
method Distribution-free two-sample testing procedures grounded in conformal outlier detection.
result Identifies valuable external data agents for model personalization.
Data-driven assistants predict congestion to optimize shared facilities efficiency.
problem Optimizing shared facilities efficiency through user coordination.
method Developed algorithms that learn from user reactions to predict congestion and achieve optimal outcomes.
result Self-fulfilling predictions can solve coordination problems in large-scale shared facilities.
Proposes a test for shared information between time series and events.
problem Detecting extreme events in time series data.
method Non-parametric statistical test using multiple two-sample testing at increasing lags.
result Outperforms or matches related tests on various datasets.
This study assesses how share capital affects financial growth of non-financial firms listed at NSE.
problem Non-financial firms listed at NSE struggle with financial growth due to declining performance and lack of investor interest.
method Descriptive and panel data analysis of 45 non-financial firms over 10 years.
result Share capital positively and significantly influences financial growth, explaining 32.73% and 11.62% of variations in earnings per share and market capitalization growth, respectively.