Gromov-Wasserstein Factorization Models for Graph Clustering. (arXiv:1911.08530v1 [cs.LG])

We propose a new nonlinear factorization model for graphs that are with topological structures, and optionally, node attributes. This model is based on a pseudometric called Gromov-Wasserstein (GW) discrepancy, which compares graphs in a relational way. It estimates observed graphs as GW barycenters constructed by a set of atoms with different weights. By minimizing the…

Robust Learning of Discrete Distributions from Batches. (arXiv:1911.08532v1 [cs.LG])

Let $d$ be the lowest $L_1$ distance to which a $k$-symbol distribution $p$ can be estimated from $m$ batches of $n$ samples each, when up to $\beta m$ batches may be adversarial. For $\beta<1/2$, Qiao and Valiant (2017) showed that $d=\Omega(\beta/\sqrt{n})$ and requires $m=\Omega(k/\beta^2)$ batches. For $\beta<1/900$, they provided a $d$ and $m$ order-optimal algorithm…

Stability of logarithmic Sobolev inequalities under a noncommutative change of measure. (arXiv:1911.08533v1 [quant-ph])

We generalize Holley-Stroock’s perturbation argument from commutative to quantum Markov semigroups. As a consequence, results on (complete) modified logarithmic Sobolev inequalities and logarithmic Sobolev inequalities for self-adjoint quantum Markov process can be used to prove estimates on the exponential convergence in relative entropy of quantum Markov systems which preserve a fixed state. This leads to…

Adversarial Robustness of Flow-Based Generative Models. (arXiv:1911.08654v1 [cs.LG])

Flow-based generative models leverage invertible generator functions to fit a distribution to the training data using maximum likelihood. Despite their use in several application domains, robustness of these models to adversarial attacks has hardly been explored. In this paper, we study adversarial robustness of flow-based generative models both theoretically (for some simple models) and empirically…

Towards Physics-informed Deep Learning for Turbulent Flow Prediction. (arXiv:1911.08655v1 [physics.comp-ph])

While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models. In this paper, we aim to predict turbulent flow by learning its highly nonlinear dynamics from spatiotemporal velocity fields of…

Predictive properties of forecast combination, ensemble methods, and Bayesian predictive synthesis. (arXiv:1911.08662v1 [math.ST])

This paper studies the theoretical predictive properties of classes of forecast combination methods. The study is motivated by the recently developed Bayesian framework for synthesizing predictive densities: Bayesian predictive synthesis. A novel strategy based on continuous time stochastic processes is proposed and developed, where the combined predictive error processes are expressed as stochastic differential equations,…

Evaluating task-agnostic exploration for fixed-batch learning of arbitrary future tasks. (arXiv:1911.08666v1 [cs.LG])

Deep reinforcement learning has been shown to solve challenging tasks where large amounts of training experience is available, usually obtained online while learning the task. Robotics is a significant potential application domain for many of these algorithms, but generating robot experience in the real world is expensive, especially when each task requires a lengthy online…

Robust Triple-Matrix-Recovery-Based Auto-Weighted Label Propagation for Classification. (arXiv:1911.08678v1 [cs.LG])

The graph-based semi-supervised label propagation algorithm has delivered impressive classification results. However, the estimated soft labels typically contain mixed signs and noise, which cause inaccurate predictions due to the lack of suitable constraints. Moreover, available methods typically calculate the weights and estimate the labels in the original input space, which typically contains noise and corruption.…

Flexural Fatigue Life of Woven Carbon/Vinyl Ester Composites under Sea Water Saturation. (arXiv:1911.08665v1 [physics.app-ph])

In this paper, the adverse effects of sea water environment on the fatigue life of woven carbon fiber/vinyl ester composites are established at room temperature. The fatigue life, defined as number of cycles to failure is determined for dry and sea water saturated composites. It is observed that the presence of sea water decreases the…