arXiv research

Robust algorithm for distributed optimization resistant to Byzantine failures.

Novel asynchronous SGD method resists Byzantine attacks without server storage.

A new machine learning method calculates failure probability efficiently and accurately.

Extends CRR model with q-binomial random walks for asset pricing.

In environments with continuous state and action spaces, state-of-the-art actor-critic reinforcement learning algorithms can solve very complex problems, yet can also fail in environments that seem trivial, but the reason for such failures is still poorly understood. In this paper, we contribute a formal explanation of…

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 …

We propose Zeno++, a new robust asynchronous Stochastic Gradient Descent~(SGD) procedure which tolerates Byzantine failures of the workers. In contrast to previous work, Zeno++ removes some unrealistic restrictions on worker-server communications, allowing for fully asynchronous updates from anonymous workers, arbitrar…

Here we prove the necessary analytic results to construct a Morse theory for the Yang-Mills-Higgs functional on the space of Higgs bundles over a compact Riemann surface. The main result is that the gradient flow with initial conditions $(A'', φ)$ converges to a critical point of this functional, the isomorphism class …

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…

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 …

We investigate the computational aspects of the basket CDS pricing with counterparty risk under a credit contagion model of multinames. This model enables us to capture the systematic volatility increases in the market triggered by a particular bankruptcy. The drawback of this problem is its analytical complication due…

In this paper, we investigate the underlying factor that leads to failure and success in the training of GANs. We study the property of the optimal discriminative function and show that in many GANs, the gradient from the optimal discriminative function is not reliable, which turns out to be the fundamental cause of fa…

Economics tool predicts failure times in reliability systems.

The paper tackles safe exploration in RL by a conservative safety critic.

Anderson and Canary have shown that if the algebraic limit of a sequence of discrete, faithful representations of a finitely generated group into PSL(2,C) does not contain parabolics, then it is also the sequence's geometric limit. We construct examples that demonstrate the failure of this theorem for certain sequences…

Unified model predicts multi-mode failure with multi-sensor data.

PAGER detects failures in deep regression models using a new framework.

Machine learning has begun to play a central role in many applications. A multitude of these applications typically also involve datasets that are distributed across multiple computing devices/machines due to either design constraints (e.g., multiagent systems) or computational/privacy reasons (e.g., learning on smartp…

Risk Advisor predicts and mitigates ML deployment failures.

CalNF models rare failures with limited data, improving safety in autonomous systems.

Prognostics and Health Management (PHM) is an emerging engineering discipline which is concerned with the analysis and prediction of equipment health and performance. One of the key challenges in PHM is to accurately predict impending failures in the equipment. In recent years, solutions for failure prediction have evo…

This work improves safety validation of autonomous vehicles by finding interpretable failures.

Framework predicts remaining useful life of DSH subsystems under unknown failure modes.

The paper calculates the likelihood of a financial market failure involving multiple major banks.

Paper proposes a method to predict disk failures using multi-layer domain adaptive learning.

We aim to predict and explain service failures in supply-chain networks, more precisely among last-mile pickup and delivery services to customers. We analyze a dataset of 500,000 services using (1) supervised classification with Random Forests, and (2) Association Rules. Our classifier reaches an average sensitivity of…

GE finds failures in autonomous systems without domain heuristics.

SGD fails to converge for deep ReLU networks with limited random initializations.

Method distinguishes between failures and domain shifts in industrial data streams.

System predicts respiratory failure up to 8 hours early.

New method avoids failures in physics-constrained systems using active learning.

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…

DeepSIP predicts network failures' impact using CNN from syslog and traffic data.

Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving averages of squared past gradients. In many applications, e.g. learning with large …

In the last two years, more than 200 papers have been written on how machine learning (ML) systems can fail because of adversarial attacks on the algorithms and data; this number balloons if we were to incorporate papers covering non-adversarial failure modes. The spate of papers has made it difficult for ML practition…

Two BO methods improve reliability optimization for rare failures.

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear rate is guaranteed when the following hold: (i) dimensions of hidden layers are…

DFMR improves robustness of learning finite mixture models in distributed settings.

New method finds failures in high-fidelity simulators with fewer steps.

Entropy-based GP adaptive design improves failure probability estimation.

Brain uses synaptic failure to sample from posterior distributions.

Asynchronous distributed machine learning solutions have proven very effective so far, but always assuming perfectly functioning workers. In practice, some of the workers can however exhibit Byzantine behavior, caused by hardware failures, software bugs, corrupt data, or even malicious attacks. We introduce \emph{Karda…

Study constructs balanced datasets for seismic failure prediction.

Proposes a deep neural network for early disk drive failure prediction.

Paper analyzes convergence of stochastic methods under heavy-tailed noise.

Improves FI-PINNs by combining re-sampling and subset simulation for better failure probability estimation.

A new algorithm learns from failures to optimize under constraints efficiently.

Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real-world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation-driven methods such as Adaptive Stress Testing (AST) have b…