Brain uses synaptic failure to sample from posterior distributions.
problem Bayesian inference in the brain's probabilistic computations.
method Adapting synaptic failure to sample posterior predictive distributions.
result Synaptic failure enables sampling of complete posterior predictive distributions.
Bayesian inference models failure distributions in autonomous systems.
problem Estimating the distribution of failures in complex systems.
method Bayesian inference using system dynamics rollouts and gradient computation.
result Improves sample efficiency and parameter space coverage in autonomous systems.
ResiliNet improves distributed neural network inference resilience.
problem Physical node failures in distributed neural networks cause performance drops.
method Skip hyperconnection and failout technique.
result ResiliNet provides inference resiliency for distributed neural networks.
Locally learned synaptic failure enables complete Bayesian inference.
problem Bayesian inference in neural networks.
method Biologically constrained neural network with synaptic failure and lateral inhibition.
result Synaptic failure allows sampling from both epistemic and aleatoric distributions.
Distributed machine learning algorithms enable learning of models from datasets that are distributed over a network without gathering the data at a centralized location. While efficient distributed algorithms have been developed under the assumption of faultless networks, failures that can render these algorithms nonfu…
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.
New research shows Byzantine failures hurt generalization more than data poisoning in robust distributed learning.
problem Generalization in robust distributed learning algorithms under Byzantine failures vs. data poisoning.
method Algorithmic stability analysis of robust distributed learning algorithms.
result Byzantine failures yield strictly worse generalization rates than data poisoning.
Economics tool predicts failure times in reliability systems.
problem Predicting optimal failure times in weighted k-out-of-n reliability systems with heterogeneous component failure.
method Using rational expectations to analyze and predict failure times in reliability systems with heterogeneous component failure.
result Different measures are optimal for predicting system failure depending on component failure distributions.
Robust algorithm for distributed optimization resistant to Byzantine failures.
problem Resilient optimization in the presence of unreliable agents.
method Temporal and spatial robust aggregation, gradient normalization.
result Convergence for strongly convex and non-convex functions.
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.
We develop a new method to estimate failure probabilities in complex systems.
problem Estimating failure probabilities in safety-critical autonomous systems is challenging due to the rarity of failures and large state spaces.
method We propose an adaptive importance sampling algorithm that minimizes forward Kullback-Leibler divergence and uses Markov score ascent methods.
result Our method provides more accurate failure probability estimates than existing techniques.
Method distinguishes between failures and domain shifts in industrial data streams.
problem Confusing domain shifts with failures in industrial data.
method Modified Page-Hinkley changepoint detector and supervised domain-adaptation-based anomaly detection.
result Allows differentiation between failures and domain shifts.
Study extreme-case Value-at-Risk under IFR distributions, providing guidance for risk management.
problem Understanding extreme-case risk measures under distributional ambiguity and increasing failure rate.
method Characterized extreme-case range Value-at-Risk under mean and variance constraints with increasing failure rate.
result Characterized specific characteristics of extreme-case distributions under IFR constraints.
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.
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.
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.
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…
SSH-Net: A Deep Neural Network for Predicting Failure Time Distribution Functions under Competing Risks with GPU Data
problem Predicting failure time distribution functions under competing risks
method Structured Segmented Hazard Deep Neural Network (SSH-Net)
result Prediction accuracy validated through simulation studies and GPU data
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.
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.
In power systems, an asset class is a group of power equipment that has the same function and shares similar electrical or mechanical characteristics. Predicting failures for different asset classes is critical for electric utilities towards developing cost-effective asset management strategies. Previously, physical ag…
Predict water pipe failures using machine learning and survival analysis.
problem Difficulty in accessing water pipes for maintenance.
method Classical and modern classifiers for short-term prediction, survival analysis for long-term forecast, and oversampling technique for imbalanced data.
result Identifies important risk factors for water pipe failures.
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
Novel asynchronous SGD method resists Byzantine attacks without server storage.
problem Asynchronous distributed learning with Byzantine attacks and failures.
method Buffered Asynchronous SGD (BASGD) and its momentum variant (BASGDm).
result BASGD and BASGDm resist non-omniscient and omniscient attacks without server storage.
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 …
Failure of the main argument for the use of heavy tailed distribution in Finance is given. More precisely, one cannot observe so many outliers for Cauchy or for symmetric stable distributions as we have in reality. keywords:outliers; financial indexes; heavy tails; Cauchy distribution; stable distributions
One of the key challenges in predictive maintenance is to predict the impending downtime of an equipment with a reasonable prediction horizon so that countermeasures can be put in place. Classically, this problem has been posed in two different ways which are typically solved independently: (1) Remaining useful life (R…
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.
Deep neural networks improve AFT model for non-linear predictors.
problem Nonlinearity in predictors of AFT models.
method Apply DNNs to fit AFT models using Gehan-type loss and sub-sampling.
result DeepR-AFT outperforms parametric and semiparametric models.
Proposes a federated learning approach for industrial asset failure prediction.
problem Lack of data and privacy concerns in industrial prognostics.
method Two-stage federated learning: dimension reduction and parameter estimation.
result Validated the approach using simulated and real data.
The 2008 financial crisis illustrated the need for a thorough, functional understanding of systemic risk in strongly interconnected financial structures. Dynamic processes on complex networks being intrinsically difficult, most recent studies of this problem have relied on numerical simulations. Here we report analytic…
New approach combines invariance and information bottleneck for OOD generalization.
problem OOD generalization failures in classification tasks.
method Revisit linear regression tasks, prove information bottleneck constraint necessary, propose combined approach.
result Combined invariance and information bottleneck approach improves OOD generalization.
The study diagnoses fairness issues in healthcare models under distribution shifts.
problem Understanding and diagnosing fairness changes in machine learning models under distribution shifts in healthcare.
method Causal framing and conditional independence tests to characterize distribution shifts.
result Knowledge of distribution shifts helps diagnose fairness transfer failures, including complex cases.
In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithm…
DFMR improves robustness of learning finite mixture models in distributed settings.
problem Learning finite mixture models in distributed settings with Byzantine failures.
method DFMR leverages pairwise L2 distances to filter and retain local estimates, ensuring robust aggregation.
result DFMR achieves optimal convergence rate and asymptotic equivalence to global maximum likelihood estimate.
We consider a model of contagion in financial networks recently introduced in the literature, and we characterize the effect of a few features empirically observed in real networks on the stability of the system. Notably, we consider the effect of heterogeneous degree distributions, heterogeneous balance sheet size and…
The growth of data, the need for scalability and the complexity of models used in modern machine learning calls for distributed implementations. Yet, as of today, distributed machine learning frameworks have largely ignored the possibility of arbitrary (i.e., Byzantine) failures. In this paper, we study the robustness …
While autonomous vehicle (AV) technology has shown substantial progress, we still lack tools for rigorous and scalable testing. Real-world testing, the de-facto evaluation method, is dangerous to the public. Moreover, due to the rare nature of failures, billions of miles of driving are needed to statisticall…
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.
Develops a method for causal inference in recurrent event data with terminal failure.
problem Causal inference in recurrent event data with a terminal event.
method Multiply robust estimation framework for causal inference.
result Proposes an estimator for the expected number of recurrent events and failure survival function.
Although standard economics textbooks are seldom interested in production networks, modern economies are more and more based upon suppliers/customers interactions. One can consider entire sectors of the economy as generalised supply chains. We will take this view in the present paper and study under which conditions lo…
In survival analysis, estimating the failure time distribution is an important and difficult task, since usually the data is subject to censoring. Specifically, in this paper we consider current status data, a type of data where all of the observations are censored. The format of the data is such that the failure time …
VAE struggles with distribution class sharpness, which can be learned dynamically.
problem VAE struggles with distribution class sharpness, leading to blurry reconstructions.
method Established that VAE fails if distribution class sharpness does not match data scale. Suggested learning distribution sharpness dynamically.
result Dynamic adjustment of distribution sharpness improves VAE performance, escaping local optima.
PAGER detects failures in deep regression models using a new framework.
problem Detecting failures in deep regression models.
method PAGER uses a combination of epistemic uncertainty and manifold non-conformity scores.
result PAGER accurately characterizes and detects failures in deep regressors.
We consider the problem of distributed statistical machine learning in adversarial settings, where some unknown and time-varying subset of working machines may be compromised and behave arbitrarily to prevent an accurate model from being learned. This setting captures the potential adversarial attacks faced by Federate…
Complex non-linear interactions between banks and assets we model by two time-dependent Erdős Renyi network models where each node, representing bank, can invest either to a single asset (model I) or multiple assets (model II). We use dynamical network approach to evaluate the collective financial failure---systemic ri…
A federated model predicts failures using multi-stream incomplete data.
problem Insufficient data for reliable prognostic models in multi-stream applications.
method Federated data fusion, multivariate functional principal component analysis, (log)-location-scale regression model, federated algorithm.
result Performance is as good as classic non-federated models and better than individual models.
Risk Advisor predicts and mitigates ML deployment failures.
problem Predicting and mitigating test-time failure risks of ML systems.
method Post-hoc meta-learner for estimating failure risks and uncertainties.
result Reliably predicts deployment-time failure risks across various ML models.