New framework tests AVs as a black box, prioritizing rare failure modes.
problem Lack of rigorous and scalable testing methods for AVs.
method Developed a simulation testing framework that learns to identify and rank failure scenarios via adaptive importance-sampling methods.
result First independent evaluation of a full-stack commercial AV system (Comma AI's OpenPilot).
Jeffreys Flow improves robustness of Boltzmann generators for rare event sampling.
problem Rare events and metastable trapping in sampling physical systems with rough energy landscapes.
method Introduces Jeffreys Flow, a robust generative framework using Parallel Tempering distillation and symmetric Jeffreys divergence to mitigate mode collapse and improve mode coverage.
result Minimizing Jeffreys divergence suppresses mode collapse and corrects inaccuracies in multi-modal distributions.
This paper addresses the problem of evaluating learning systems in safety critical domains such as autonomous driving, where failures can have catastrophic consequences. We focus on two problems: searching for scenarios when learned agents fail and assessing their probability of failure. The standard method for agent e…
Develops a method to simulate rare dangerous events in autonomous systems.
problem Rare dangerous events in safety-critical systems are hard to test in real-world settings.
method Combines exploration, exploitation, and optimization techniques for rare-event simulation.
result Provides rigorous guarantees for the performance of the method.
Unified model predicts multi-mode failure with multi-sensor data.
problem Independent failure mode and RUL prediction ignores inherent relationship.
method Hierarchical Bayesian framework with Cox model, Gaussian process, and multinomial distributions.
result Robust uncertainty quantification and accurate prediction of multi-mode failure.
Framework predicts remaining useful life of DSH subsystems under unknown failure modes.
problem Predicting remaining useful life of DSH subsystems with unknown failure modes.
method Unsupervised framework using mixture of Gaussian regressions and Expectation-Maximization algorithm.
result Improved prediction accuracy and interpretability of RUL.
In this paper, we consider a problem of failure prediction in the context of predictive maintenance applications. We present a new approach for rare failures prediction, based on a general methodology, which takes into account peculiar properties of technical systems. We illustrate the applicability of the method on th…
CalNF models rare failures with limited data, improving safety in autonomous systems.
problem Challenges in modeling and debugging rare safety-critical failures due to limited data.
method CalNF, a self-regularized framework for posterior learning from limited data.
result Achieves state-of-the-art performance on data-limited failure modeling and inverse problems.
This research improves asset life prediction by integrating deep learning with mixture distributions.
problem Predicting residual useful life for assets with multiple failure modes.
method Integrates mixture (log)-location-scale distribution with deep learning.
result Proposed models outperform existing methods in predicting residual useful life.
Study identifies failure modes of machine learning models in out-of-distribution settings.
problem Machine learning models fail to generalize well to new, unseen data.
method Theoretical study of gradient-descent-trained linear classifiers on easy-to-learn tasks, followed by experiments on modern neural networks.
result Two failure modes of spurious correlations are uncovered: geometric and statistical.
We identify and study two common failure modes for early training in deep ReLU nets. For each we give a rigorous proof of when it occurs and how to avoid it, for fully connected and residual architectures. The first failure mode, exploding/vanishing mean activation length, can be avoided by initializing weights from a …
A new method estimates rare failure events in complex systems.
problem Estimating the probability of rare failure events in non-linear systems.
method Stochastic Spectral Embedding (SSE) combined with modifications for efficient rare event estimation.
result Rare failure probability decomposed into conditional probabilities for easier computation.
Framework classifies machine learning failures into intentional and unintentional.
problem Understanding and preventing failures in machine learning systems.
method Developed a taxonomy of machine learning failure modes.
result Stakeholders found the framework useful for discussing machine learning failures.
DG separates successes and failures by gating updates with advantage and surprisal.
problem Negative learning from surprising data in distributed reinforcement learning.
method DG gates each update with the product of advantage and surprisal, suppressing failures and preserving successes.
result DG outperforms other methods in various challenging reinforcement learning tasks.
A new method normalizes activations to match batch normalization without batch dependence.
problem Performance degradation with batch-independent normalization techniques.
method Proxy-Normalizing Activations
result Proxy-Normalization technique emulates batch normalization's behavior and performance.
Two BO methods improve reliability optimization for rare failures.
problem Maximizing reliability of designs subject to random perturbations.
method Bayesian optimization with Thompson sampling and knowledge gradient.
result Proposed methods outperform existing techniques in extreme failure probability scenarios.
Study constructs balanced datasets for seismic failure prediction.
problem Imbalanced datasets limit machine learning performance in seismic failure prediction.
method Framework with three steps: GMF identification, probability density estimation, and sample transformation.
result Framework improves machine learning performance in seismic failure mode prediction.
Revisits PPO design choices, exposing failure modes and proposing alternatives.
problem Failure modes of standard PPO in new environments.
method Revisits standard PPO design choices, exposes failure modes, and proposes alternative approaches.
result Alternative design choices prevent failure modes in new environments.
Evaluation and validation of complicated control systems are crucial to guarantee usability and safety. Usually, failure happens in some very rarely encountered situations, but once triggered, the consequence is disastrous. Accelerated Evaluation is a methodology that efficiently tests those rarely-occurring yet critic…
This paper characterizes VAE training pathologies and their effects on tasks.
problem Characterizing VAE training pathologies and their impact on downstream tasks.
method Concretely characterizing conditions for VAE training pathologies and their connection to specific downstream tasks.
result Connects VAE training pathologies to specific downstream tasks like learning compressed and disentangled representations, adversarial robustness, and semi-supervised learning.
Proposes IIB for domain generalization, overcoming failure modes of IRM.
problem Domain generalization with nonlinear classifiers and pseudo-invariant features.
method Invariant Information Bottleneck (IIB) using mutual information and variational formulation.
result Significantly outperforms IRM on synthetic datasets and real-world benchmarks.
Schervish (1985b) showed that every forecasting system is noncalibrated for uncountably many data sequences that it might see. This result is strengthened here: from a topological point of view, failure of calibration is typical and calibration rare. Meanwhile, Bayesian forecasters are certain that they are calibrated-…
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
Unified theory explains two failure modes of deep transformers and provides initialisation guidelines.
problem Two failure modes (rank collapse and entropy collapse) of self-attention layers in deep transformers.
method Analytical theory of signal propagation through deep transformers, using the Random Energy Model analogy.
result Simple algorithm to compute trainability diagrams for correct initialisation hyper-parameters.
The loss of a few neurons in a brain rarely results in any visible loss of function. However, the insight into what "few" means in this context is unclear. How many random neuron failures will it take to lead to a visible loss of function? In this paper, we address the fundamental question of the impact of the crash of…
There are several distinct failure modes for overoptimization of systems on the basis of metrics. This occurs when a metric which can be used to improve a system is used to an extent that further optimization is ineffective or harmful, and is sometimes termed Goodhart's Law. This class of failure is often poorly unders…
Proposes a method to refine PDE-driven high-dimensional rare-event simulation.
problem Challenges in constructing accurate surrogates for rare-event simulation.
method Adaptive importance sampling framework that refines a locally constructed surrogate.
result Achieves accuracy comparable to true-model adaptive importance sampling with fewer high-fidelity evaluations.
Mathematical analysis shows annealing prevents mode collapse in Gaussian mixtures.
problem Mode collapse in variational inference for multimodal distributions.
method Analyzed annealing strategies for Gaussian mixtures, derived formulas, and tested on neural networks.
result Appropriately chosen annealing schemes can robustly prevent mode collapse.
A new method combines MCMC results to avoid failures in parallel computing.
problem Parallel MCMC's sensitivity to subposterior sampling issues leads to failures.
method Parallel Active Inference (PAI) uses Gaussian Process (GP) surrogate modeling and active learning.
result PAI successfully combines MCMC results where previous methods fail.
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.
Active Kriging Monte Carlo simulation method with conformal certification for failure probability estimation
problem Failure probability estimation in structural reliability analysis
method Active learning framework with conformal prediction
result Improved uncertainty quantification and reliability of failure probability estimates
Simplified non-contrastive learning avoids representation collapse.
problem Training failure modes in self-supervised learning.
method Hyperdimensional computing and inductive bias.
result The approach avoids representation collapses.
New approach uses dynamic programming to efficiently discover failures in autonomous vehicle simulations.
problem Efficiently discovering rare failure events in autonomous vehicle simulations.
method Approximate dynamic programming and scene decomposition to estimate failure distribution.
result Increased number of failures discovered compared to baseline approaches.
Differentiable methods fail due to spectral issues in Jacobians.
problem Chaos-based failures in differentiable programming.
method Trace failures to the spectrum of Jacobians.
result Criteria for avoiding spectral failure in optimization.
Efficiently estimates rare events using multifidelity modeling.
problem Estimating rare events with computationally expensive models.
method Active learning with multifidelity modeling, adapting the number of high-fidelity simulations based on problem complexity and desired accuracy.
result Significantly reduced the number of high-fidelity model calls while maintaining accuracy.
Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to …
Adaptive Stress Testing detects financial fraud by simulating potential failures.
problem Detecting and mitigating vulnerabilities in financial systems.
method Developed a simplified model using historical data and reinforcement learning.
result Identified the most likely path to system failure and improved fraud detection.
This work aims to reduce inexplicable errors in deep neural networks by obtaining class-level semantics and penalizing misclassifications.
problem Deep neural networks misclassify images, leading to inexplicable errors that can harm trust and societal impact.
method Obtain class-level semantics, propose Weighted Loss Functions (WLFs), and train classifiers with these methods.
result Trained networks have more explicable failure modes and comparable accuracy to existing methods.
This paper evaluates data enrichment techniques for rare event detection in manufacturing.
problem Rare events in manufacturing lead to unplanned downtime and high energy consumption.
method Time series data augmentation, sampling, and imputation techniques combined with supervised machine learning.
result Data enrichment enhances rare failure event detection and prediction by up to 48%.
Adaptive auditing improves AI robustness testing with anytime-valid guarantees.
problem Cost and time of annotation limit rigorous AI failure mode characterization.
method Introduces hypothesis testing framework for adaptive audits using SAVI.
result Proves anytime-valid type-I error control and robustness certification.
New model explains GAN training dynamics and mode collapse.
problem Mode collapse in GANs, where generators fail to reproduce diversity.
method Simplified model using particles in output space, coupled by universal kernel.
result Gradient regularizers can optimally yield convergence through critical damping.
Proposes a federated learning approach for RUL prediction from nonparametric degradation and failure signals.
problem Cost-effective RUL prediction from limited, non-shared CM signals with unknown parametric forms.
method Joint modeling of nonlinear degradation signals and failure events using federated learning.
result Superior RUL prediction compared to alternatives, validated through simulations and real data.
This paper presents a method to efficiently estimate rare event probabilities using a combination of high and low-fidelity models.
problem Estimating the probability of failure for complex systems using high-fidelity models is expensive and inaccurate for rare events.
method The paper introduces a multi-fidelity surrogate modeling strategy using active learning and subset simulation to merge high and low-fidelity models.
result The method significantly reduces computational cost while maintaining high accuracy in estimating rare event probabilities.
HalluWorld benchmarks hallucinations in language models across diverse tasks.
problem Inconsistent benchmarks of hallucination in language models.
method Explicit reference-world formulation, synthetic and semi-synthetic environments, controlled variation of world complexity.
result Models struggle with perceptual hallucination but not multi-step state tracking.
Low-rank MPPCA improves importance sampling in high dimensions.
problem Estimating full-rank GMM covariance matrices in high dimensions is numerically unstable.
method Use MPPCA mixtures as low-rank proposals for importance sampling in high-dimensional spaces.
result Consistent gains in sample efficiency and quality of failure distribution characterization.
We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. Such success-failure rewards are often …
Conformal prediction fails to cover minority classes in imbalanced datasets, but a class-conditional fix improves coverage.
problem Conformal prediction fails to cover minority classes in imbalanced datasets, leading to poor performance on rare labels.
method Class-conditional conformal prediction to improve coverage of minority classes.
result Class-conditional conformal prediction restores minority coverage to target with a modest increase in prediction-set size.
New method combines FMEA and Bayesian Network for root cause analysis in lithium-ion battery production.
problem Complex cause-effect relationships in lithium-ion battery production.
method Combining FMEA with Bayesian Network to detect and resolve inconsistencies.
result Holistic method builds large-scale cross-process Bayesian Failure Network for root cause analysis.