New algorithm estimates eigenspace with faulty nodes, matching performance of existing methods.
problem Estimating eigenspace in distributed systems with node failures.
method Develops an eigenspace estimation algorithm for distributed environments with arbitrary node failures.
result Matches performance of existing non-robust estimator up to an additive error.
This paper maps the insurability of AI risks across various insurance products.
problem Emerging AI risks and their implications for insurance coverage.
method Coding 55 AI threat classes against 26 insurance products using public carrier materials and threat catalogs.
result Identification of a four-tier insurability frontier: affirmatively insured, silent-AI exposures, actively excluded, and unstructured perils.
In this paper we explore continuous silent speech recognition using electroencephalography (EEG) signals. We implemented a connectionist temporal classification (CTC) automatic speech recognition (ASR) model to translate EEG signals recorded in parallel while subjects were reading English sentences in their mind withou…
Silent abandonment reduces contact center efficiency by 5%-15%.
problem Measuring customer abandonment and patience in text-based contact centers is challenging due to uncertainty.
method Developed methodologies to identify silent-abandonment customers and estimate customer patience using text analysis and queueing models.
result Silent abandonment accounts for 30%-67% of customer abandonments and reduces system efficiency by 5%-15%.
Neural networks can learn kernel machines with a data-dependent kernel.
problem Can neural networks in the rich feature learning regime learn a kernel machine?
method Demonstrated silent alignment effect in neural networks, showing they can learn a kernel machine with a data-dependent kernel.
result Neural networks in the rich feature learning regime can learn a kernel machine with a data-dependent kernel due to silent alignment.
Lipreading has a lot of potential applications such as in the domain of surveillance and video conferencing. Despite this, most of the work in building lipreading systems has been limited to classifying silent videos into classes representing text phrases. However, there are multiple problems associated with making lip…
The wave trace of certain convex domains can be smooth near some points in the length spectrum.
problem Understanding the relationship between the wave trace and the length spectrum of convex domains.
method Constructing silent periodic billiard orbits with the same length but different Maslov indices, using a microlocal parametrix for wave invariants.
result The wave trace can be smooth near some points in the length spectrum, showing potential limitations for inverse spectral problems.
The increasing popularity of cell phones has made them the most personal and ubiquitous communication devices nowadays. Typically, the ringing notifications of mobile phones are used to inform the users about the incoming calls. However, the notifications of inappropriate incoming calls sometimes cause interruptions no…
Diverging Flows detects extrapolations in flow models, ensuring reliable predictions.
problem Flow models extrapolate into invalid data, leading to silent failures.
method Structurally enforce inefficient transport for off-manifold inputs.
result Effective detection of extrapolations without compromising predictive fidelity or inference latency.
Develops geometric framework for analyzing big bang singularities without symmetry assumptions.
problem Analyzing big bang singularities without symmetry constraints.
method Geometric framework combined with Einstein's equations.
result Partial improvements of assumptions on expansion normalised Weingarten map and convergence of K. Deep learning maps tongue movements to speech sounds for voiceless individuals.
problem Developing silent speech interfaces for individuals without a larynx.
method Hybrid spatio-temporal 3D convolutions and feature shuffling for formant estimation and tracking from ultrasound tongue images.
result Best model achieves R-squared of 99.96% for vowel formant regression.
Markov Chain Monte Carlo (MCMC) algorithms are a workhorse of probabilistic modeling and inference, but are difficult to debug, and are prone to silent failure if implemented naively. We outline several strategies for testing the correctness of MCMC algorithms. Specifically, we advocate writing code in a modular way, w…
The study proposes a framework to accept OOD data based on competence scores.
problem Silent failures in Domain Generalization where models reject OOD data without proper justification.
method A learning to reject framework using proxy incompetence scores to predict trustworthiness.
result Increasing incompetence scores are predictive of reduced accuracy, but not always favorable for accuracy/rejection trade-off.
Extracting and detecting spike activities from the fluorescence observations is an important step in understanding how neuron systems work. The main challenge lies in that the combination of the ambient noise with dynamic baseline fluctuation, often contaminates the observations, thereby deteriorating the reliability o…
Feedback alignment methods need to be evaluated for accuracy and gradient cosine similarity.
problem Evaluating feedback alignment methods
method Proposed diagnostic evaluation protocol
result Identified silent failures in standard reporting pair
Develops geometric framework for uncertainty-aware multi-class classification.
problem Silent failure of AI models when uncertain, especially in multi-class settings.
method Geometric framework treating probability vectors as points on the (c−1)-dimensional probability simplex, using Fisher--Rao metric for calibration and uncertainty quantification. result Empirical validation shows 72.5% of errors captured while deferring 34.5% of ambiguous predictions, reducing automated decision error rates from 16.8% to 6.9%.
Decoding language representations directly from the brain can enable new Brain-Computer Interfaces (BCI) for high bandwidth human-human and human-machine communication. Clinically, such technologies can restore communication in people with neurological conditions affecting their ability to speak. In this study, we prop…
We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to fail silently. This paper explores the problem of building ML systems that fail …
We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably. Till recently, domain adaptation methods assumed the aligned class spaces, such that reducing distribution divergence makes the transfer between domains easier. Su…
A new method corrects bias in machine learning for trading by filtering out non-executable prices.
problem Contaminated data from price limits causes misleading performance metrics in trading models.
method Mask-first design with tradability filters, GPU optimization, and penalized losses.
result The system achieves Sharpe ratios of 1.63 on real data, significantly outperforming existing methods.
Study uses machine learning and survival analysis to predict CKD progression.
problem Early detection and management of CKD to reduce ESRD risk.
method Combines machine learning and classical statistical models to identify novel CKD progression predictors.
result Deep learning models outperform other methods in predicting CKD progression.
Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose a feed-forward neural network capable of semi-supervised learning on manifolds w…
We study the problem of source separation for music using deep learning with four known sources: drums, bass, vocals and other accompaniments. State-of-the-art approaches predict soft masks over mixture spectrograms while methods working on the waveform are lagging behind as measured on the standard MusDB benchmark. Ou…
Online monitor detects classifier drift and adapts predictions.
problem Silent degradation of classifier accuracy under distributional shift.
method Sliding-window KS statistic with calibrated alarm thresholds.
result 86.6% valid detection across various shift conditions.
Bayesian approach improves uncertainty in deep learning models.
problem Uncertainty quantification in deep learning models.
method Bayesian point of view, Gaussian approximability, semi-parametric Bernstein-von Mises theorems.
result Bayesian credible regions have valid frequentist coverage, providing theoretical justification for deep learning.
The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by the many vulnerabilities reported on a daily basis. This calls for machine learning methods for vulnerability detection. Deep learning is attractive for this purpose because it a…
PIVOT bridges Black-Scholes price and implied volatility spaces via a differentiable layer.
problem Lack of a differentiable interface between price and implied volatility spaces.
method Develops PIVOT, a differentiable layer that preserves LBR's forward pass and avoids backpropagation through branch logic, addressing singularity issues.
result PIVOT achieves high performance and accuracy, reducing price and implied volatility errors by up to 43.4% and 21.3% respectively.
In this paper we address the problem of tracking multiple speakers via the fusion of visual and auditory information. We propose to exploit the complementary nature of these two modalities in order to accurately estimate smooth trajectories of the tracked persons, to deal with the partial or total absence of one of the…
This work improves neural network trustworthiness through uncertainty estimation.
problem Overconfident neural networks lead to poor performance under distribution shifts.
method Develops a general uncertainty framework for neural networks, including classification with rejection.
result Improves model trustworthiness and robustness in decision-making tasks.
Machine learning models fail due to concept and data drift during pandemic.
problem Machine learning models trained before the pandemic are unreliable during the pandemic.
method Detect and diagnose concept and data drift in models.
result Model resilience and robustness are crucial for future predictions.
Unified framework detects overfitting in crash classification models.
problem Evaluation metrics fail to detect overfitting in crash classification models.
method Random Matrix Theory and Heavy-Tailed Self-Regularization framework applied to various model types.
result Power-law exponent α reliably distinguishes well-regularized from overfit models.
Confidence bands for tuning curves improve hyperparameter comparison in NLP.
problem Ambiguity in comparing hyperparameter tuning methods.
method Constructs exact, simultaneous, and distribution-free confidence bands for tuning curves.
result Confidence bands provide a robust basis for comparing methods rigorously.
Paper tackles HMM learning with unknown missing observation locations.
problem Learning HMMs with missing data locations unknown.
method Proposes reconstruction algorithms without structural assumptions.
result Can reconstruct process dynamics as if missing locations were known.
ECGDetect uses deep learning to detect ischemia in heart ECGs.
problem Detecting early signs of acute coronary syndrome in patients.
method Developed a deep learning model using the LTST database.
result Deep neural network achieved 90.31% ROC-AUC, 89.34% sensitivity, 87.81% specificity.
Regularization and data augmentation can be class-dependent, leading to poor performance on some classes.
problem Class-dependent effects of regularization and data augmentation.
method Evaluation of regularization and data augmentation techniques on Imagenet and INaturalist datasets.
result Regularization and data augmentation can lead to significant performance drops on some classes.
Three training methods for language models are shown to be variations of one another.
problem Training language models to reason effectively using different methods.
method Three training methods: GRPO, Dr. GRPO, and DAPO.
result All three methods adjust a single number: standard deviation, measuring disagreement in answers.
Study improves CNN medical image segmentation accuracy and reliability.
problem Over-confident predictions and silent failures in out-of-distribution data.
method Multi-task learning and spectral analysis of CNN feature maps.
result Joint multi-task learning models outperform dedicated models and detect OOD data more accurately.
Audit shows risk claims from distributional reinforcement learning agents are often false.
problem Evaluating the risk claims made by distributional reinforcement learning agents.
method Combines a decision-relevant screening metric, ground truth from Monte Carlo, and statistical methods to audit risk claims.
result 40-95% of the strongest risk claims are refuted, indicating the learned risk reflects a training artifact rather than environment stochasticity.
Deleting refusal directions from models leads to systematically more optimistic decisions.
problem The impact of removing refusal directions from models on decision-making outcomes.
method Ablation study using a frozen pipeline of 21,600 weekly equity decisions.
result Ablation of refusal directions makes models more optimistic and justifies themselves more, but also reduces confidence.
Physics-Informed Neural Networks (PINNs) benchmarked against clinical estimator and reveal parameter identifiability
problem Chemotherapy pharmacokinetics (PK) with tissue concentration not measured
method Physics-Informed Neural Networks (PINNs) benchmarked against clinical estimator and reveal parameter identifiability
result PINN recovers tissue concentration and identifies non-identifiable parameters
This work bounds classification error in machine learning for low Bayes error conditions.
problem Understanding the error mismatch between Bayes error and model-based classification error.
method Applying classification error bounds to study the relationship with Kullback-Leibler divergence and proposing a linear approximation for low Bayes error conditions.
result A linear approximation of the classification error bound for low Bayes error conditions is proposed.
Paper assesses error estimates of Random Forests classification.
problem Quantitative assessment of Random Forests error estimates.
method Theoretical and empirical investigation of various error estimation methods.
result Random Forests' error estimates are closer to true error rate than average prediction error.
This paper tackles worst-class error rate in classification tasks.
problem Minimizing worst-class error rate in classification tasks, especially in medical image classification.
method Designing a boosting approach to bound the worst-class error rate using Deep Neural Networks (DNNs).
result The proposed boosting approach lowers worst-class test error rates while avoiding overfitting.
Study identifies and analyzes three types of errors in learning Fourier operators.
problem Statistical, discretization, and truncation errors in learning Fourier operators.
method Analysis of a Discrete Fourier Transform (DFT) based least squares estimator.
result Established upper and lower bounds on statistical, discretization, and truncation errors.
This paper examines error bounds for deep learning classifiers with noisy labels.
problem Understanding the performance of classifiers trained on noisy data.
method Derives error bounds for excess risk, decomposing it into statistical and approximation errors. Uses independent block construction for statistical dependencies and vector-valued setting for approximation error.
result Established theoretical results for error bounds in deep learning with noisy labels, mitigating the impact of high-dimensional input spaces.
The paper analyzes CycleGAN's error components for unpaired data generation.
problem Analyzing approximation and estimation errors in CycleGAN for unpaired data.
method Decomposes risk into approximation and estimation errors, analyzing each separately and considering their trade-offs.
result Theoretical insights into CycleGAN's performance through error analysis.
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.
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.