New method for group testing robust to errors in group membership specifications.
problem Errors in specifying group memberships during group testing.
method Debiased Robust Lasso Test Method (DRLT) based on Lasso debiasing.
result Extends LASSO bias mitigation to handle group membership specification errors.
Identifies patient-specific root causes of disease using structural equation models.
problem Detecting significant variables in complex diseases that differ between patients.
method Defining patient-specific root causes as exogenous errors in a structural equation model, quantifying predictivity using Shapley values, and developing a fast algorithm called Root Causal Inference.
result Significant improvements in accuracy by uncovering root causes with large effect sizes at the individual level but clinically insignificant effect sizes at the group level.
Proposes a new test for validating multivariate dynamic regression models.
problem Inadequate exogeneity conditions for conventional model specification tests in dynamic systems.
method Develops a generalized Durbin estimator for multiple-equation systems with dynamic dependencies, and constructs Wald tests.
result Bootstrap-based Wald tests improve finite-sample size control and validate the null hypothesis in multifactor models.
We design a new algorithm for the Euclidean k-means problem that operates in the local model of differential privacy. Unlike in the non-private literature, differentially private algorithms for the k-means objective incur both additive and multiplicative errors. Our algorithm significantly reduces the additive erro…
This paper studies a specific blow-up algorithm for sop polynomials and their RLCT.
problem Determining the RLCT of sum-of-products polynomials through blow-up.
method Investigates a specific blow-up algorithm for sop polynomials to resolve their singularities.
result It is possible to resolve the singularities of sop polynomials using a specific blow-up algorithm.
Study evaluates Deep PDE solvers for high-dimensional option pricing, identifying key sources of error.
problem Empirical study on error analysis of Deep PDE solvers for high-dimensional option pricing.
method Comparative experiments with Deep BSDE method and other solvers, identifying three main sources of error.
result Deep BSDE method is superior and robust to option specifications, improving with larger batch sizes and fewer time steps.
Combines cost-sensitive and Neyman-Pearson paradigms for better binary classification.
problem Asymmetric binary classification problems with unequal error severities.
method Develops TUBE-CS algorithm to bridge cost-sensitive and Neyman-Pearson paradigms.
result High-probability control of population type I error.
New bounds study class-specific generalization error in machine learning.
problem Existing generalization theories assume uniform class performance, but in practice, classes vary significantly.
method Developed novel information-theoretic bounds using KL divergence and CMI.
result Theoretical bounds accurately capture complex class-generalization error behavior.
New model identifies patient-specific disease root causes.
problem Identifying root causes of complex diseases varying between patients.
method Generalized Root Causal Inference (GRCI) algorithm for heteroscedastic noise model.
result GRCI accurately extracts patient-specific root causes.
The study analyzes transfer learning using information theory.
problem Transfer learning in different distributions.
method Information-theoretic analysis, focusing on KL divergence.
result Upper bounds for general transfer learning algorithms and specific ERM.
We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…
Study analyzes error in ReLU networks with local connections.
problem Improving neural network performance and understanding approximation errors.
method Analyzed approximation error of ReLU networks with local connections.
result Error estimate depends on depth and width of hidden layers.
New method identifies root causes in presence of latent confounding.
problem Identifying root causes in the presence of latent variables.
method Extract Errors with Latents (EEL) procedure for inferring root causes.
result Superior accuracy and robustness compared to previous methods.
Non-convex SGD learns halfspaces with adversarial label noise efficiently.
problem Agnostically learning halfspaces in adversarial label noise settings.
method Non-convex SGD optimization for halfspace learning.
result Non-convex SGD achieves misclassification error close to optimal with adversarial noise.
Language models fail to execute simple steps, showing gating and binding errors.
problem Procedural hallucinations in language models, failing to execute simple steps.
method Analyzed long-context binding tasks, identifying gating and binding errors.
result Procedural errors are due to gating and binding failures, with recency bias contributing to the latter.
Paper develops robust neural network sensors for fuel injection quantities.
problem Adversarial noise increases error in standard neural network models for fuel injection measurements.
method Apply provable robust network learning and verification methods to fuel injection measurements.
result Provable robust model reduces mean relative error to 16.5% under sensor noise.
New bounds show current methods overestimate system parameter errors.
problem Current bounds overestimate parameter errors in system identification.
method Utilized asymptotic normality and second-order decomposition.
result Obtained finite-sample bounds matching optimal rates up to constants.
This paper extends the earlier work on an oscillating error correction technique. Specifically, it extends the design to include further corrections, by adding new layers to the classifier through a branching method. This technique is still consistent with earlier work and also neural networks in general. With this ext…
The paper offers error bounds for quantized dynamical models.
problem Accuracy of dynamical models from dependent data sequences.
method Developed uniform error bounds for quantized models and imperfect optimization algorithms.
result Unified bounds for slow and fast rates, scaling with model encoding bits.
This paper tightens the generalization error bound for graph embedding in non-Euclidean spaces.
problem High generalization error in non-Euclidean graph embedding, preventing practical applications.
method Novel upper bound of graph embedding's generalization error using local Rademacher complexity.
result The new bound is tighter and faster, allowing better performance in non-Euclidean spaces.
Sharp bounds found on expert error in binary advice aggregation.
problem Aggregating binary advice from conditionally independent experts.
method Sharp upper and lower bounds on optimal error probability in asymmetric case.
result Sharp bounds recover and sharpen known results in symmetric case.
We propose a novel framework of the model specification test in regression using unlabeled test data. In many cases, we have conducted statistical inferences based on the assumption that we can correctly specify a model. However, it is difficult to confirm whether a model is correctly specified. To overcome this proble…
Method estimates LLM error rates using Pareto optimization.
problem Quantifying error rates in text-generating models.
method Pareto optimization for generating risk scores.
result Risk scores correlate well with true error rates.
Karl Menger's 1934 paper on the St. Petersburg paradox contains mathematical errors that invalidate his conclusion that unbounded utility functions, specifically Bernoulli's logarithmic utility, fail to resolve modified versions of the St. Petersburg paradox.
Kernel balancing weights are generalized as KRRR, providing better confidence intervals for treatment effects.
problem Lack of generalization error, correct feature specification, and limited to average effects.
method Interpreting kernel balancing weights as KRRR, relaxing feature specification, and extending Gaussian approximation.
result KRRR provides strong generalization properties and justifies confidence sets for causal functions.
Extends phase retrieval methods to handle sensing vector errors.
problem Phase retrieval with errors in sensing vectors.
method Total Least Squares (TLS) framework applied to gradient descent.
result Gradient descent can efficiently solve TLS phase retrieval.
Develops a method to estimate rare-event probabilities under distributional uncertainty.
problem Distributional uncertainty limits the effectiveness of rare-event simulation techniques.
method Wasserstein distributionally robust rare-event simulation (DRIS) framework.
result DRIS achieves vanishing relative error in estimating rare-event probabilities.
New bounds show multicalibration error is close to prediction error.
problem Addressing fairness in machine learning systems.
method Sample complexity bounds for uniform convergence of multicalibration error.
result Uniform convergence guarantees for multicalibration error, independent of prediction error.
New method detects causal relationships from noisy measurements.
problem Discover causal relationships from noisy, imperfect measurements.
method Transformed Independent Noise (TIN) condition and ordered group decomposition.
result Identifies causal graph structure without over-complete ICA.
Curiosity-Critic improves world model training by focusing on cumulative prediction error.
problem Training world models with intrinsic rewards that consider cumulative prediction error.
method Curiosity-Critic uses a surrogate reward based on the difference between current and asymptotic prediction errors, estimated online by a co-trained critic.
result Curiosity-Critic outperforms other methods in training speed and final world model accuracy.
CB-SLICE identifies concept-based error slices in deep learning models.
problem Systematic errors in deep learning models on specific groups.
method Concept Bottleneck Models (CBMs) and concept representations.
result CB-SLICE outperforms state-of-the-art methods in error slice identification.
Paper shows how gradient concentration helps in learning from inexact data.
problem Learning from inexact and stochastic training data.
method Combines probabilistic gradient concentration with inexact optimization techniques.
result Derives sharp test error guarantees for learning.
Adapts causal inference for high-dimensional treatments like text strings.
problem Predicting effects of interventions with many possible variations.
method Adapts classical causal estimators to high-dimensional treatment spaces, balancing moment errors.
result Shows high-dimensional treatment spaces can be addressed with a single model.
We find a deterministic equivalent for random feature regression's test error, independent of feature map dimension.
problem Understanding the generalization performance of random feature ridge regression.
method We derive a deterministic equivalent for the test error of RFRR under a concentration property, showing it can be approximated by a closed-form expression dependent on feature map eigenvalues.
result Our approximation guarantee is non-asymptotic, multiplicative, and independent of the feature map dimension, providing a tight result for the smallest number of features achieving optimal minimax error rate.
In this paper, we prove that some Gaussian structural equation models with dependent errors having equal variances are identifiable from their corresponding Gaussian distributions. Specifically, we prove identifiability for the Gaussian structural equation models that can be represented as Andersson-Madigan-Perlman cha…
End-to-end ASR error detection using audio-transcript entailment.
problem Detecting transcription errors in ASR systems to prevent error propagation.
method Proposes a novel end-to-end approach using audio-transcript entailment, with acoustic and linguistic encoders.
result Achieves CER of 26.2% on all transcription errors and 23% on medical errors specifically, improving by 12% and 15.4% respectively over a strong baseline.
Bayesian framework tackles measurement error in covariates.
problem Misleading inference due to corrupted covariates.
method Bayesian Nonparametric Learning framework robust to misspecification.
result General framework for Classical and Berkson error models.
Energy-efficient detection of natural errors in deep networks.
problem Deep networks lack error detection capability without additional energy costs.
method Append RACs at hidden layers to detect natural errors with early classification termination.
result Early classification termination reduces energy consumption.
New GLS estimator handles high-dimensional data with autocorrelated errors.
problem High-dimensional regressions with autocorrelated errors.
method LASSO regression, autoregressive model fitting, and whitening.
result The method outperforms unadjusted LASSO in estimating errors driven by autoregressive processes.
Unified error analysis for discrete flow models.
problem Error analysis of discrete flow models.
method Stochastic calculus theory, Girsanov theorem, generator matching, uniformization.
result First error analysis for discrete flow models.
Quantizes neural networks using frame theory for improved accuracy.
problem Improving neural network efficiency and accuracy through quantization.
method Sigma-Delta (ΣΔ) quantization with finite unit-norm tight frames. result Error bound between original and quantized neural networks derived.
Paper tackles fairness in CCA by minimizing correlation disparity error.
problem Fairness issues in CCA.
method Framework to minimize correlation disparity error in CCA.
result Reduces correlation disparity error without sacrificing CCA accuracy.
The success of deep learning has led to a rising interest in the generalization property of the stochastic gradient descent (SGD) method, and stability is one popular approach to study it. Existing works based on stability have studied nonconvex loss functions, but only considered the generalization error of the SGD in…
Hardness proof for agnostically learning halfspaces from worst-case lattice problems.
problem Agnostically learning halfspaces in the presence of noise.
method Reduction to worst-case lattice problems (GapSVP, SIVP).
result No efficient algorithm can achieve misclassification error better than 1/2 - γ under given hardness assumptions.
The paper uses neural networks to forecast time series data.
problem Forecasting high-dimensional stationary processes.
method Encoder-decoder neural network structure to model past observations.
result Upper bounds for forecast error under specific assumptions.
Error-robust multi-view clustering tackles noisy data across multiple sources.
problem Error in multi-view data degrades clustering performance.
method Blind clustering without error consideration is ineffective. Various approaches like sparsity, graph, subspace, and deep learning are reviewed.
result Error-robust multi-view clustering improves clustering accuracy even with corrupted data.
DD algorithm tracks test error from train error without validation data.
problem Systematic generalization gap between train and test errors in modern model training.
method Decoupled descent (DD) algorithm that cancels data reuse biases via approximate message passing.
result DD algorithm rigorously demonstrates zero-cost validation and 100% data utilization.
Study evaluates how much knowledge LLMs have by comparing their prediction accuracy to flexible models.
problem Evaluating the predictive power of LLMs without access to their training data.
method Equivalent sample size measure, comparing LLM's prediction error to flexible models trained on varying amounts of domain-specific data.
result LLMs encode varying amounts of predictive information across different economic variables.