Search Results for author:
Found 8 papers, 2 papers with code
MANDERA: Malicious Node Detection in Federated Learning via Ranking
Although we know that the benign gradients and Byzantine attacked gradients are distributed differently, to detect the malicious gradients is challenging due to (1) the gradient is high-dimensional and each dimension has its unique distribution and (2) the benign gradients and the attacked gradients are always mixed (two-sample test methods cannot apply directly).
Additive Poisson Process: Learning Intensity of Higher-Order Interaction in Poisson Processes
We present the Additive Poisson Process (APP), a novel framework that can model the higher-order interaction effects of the intensity functions in Poisson processes using projections into lower-dimensional space.
Learning Joint Intensity in a Multivariate Poisson Process on Statistical Manifolds
Learning of the model is achieved via convex optimization, thanks to the dually flat statistical manifold generated by the log-linear model.
A Deep Architecture for Log-Linear Models
We present a novel perspective on deep learning architectures using a partial order structure, which is naturally incorporated into the information geometric formulation of the log-linear model.
Additive Poisson Process: Learning Intensity of Higher-Order Interaction in Stochastic Processes
We present the Additive Poisson Process (APP), a novel framework that can model the higher-order interaction effects of the intensity functions in stochastic processes using lower dimensional projections.
Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training
On the other hand, there is smaller fraction of examples that contain all modalities (\emph{paired} data) and furthermore each modality is high dimensional when compared to number of datapoints.
Hierarchical Probabilistic Model for Blind Source Separation via Legendre Transformation
We present a novel blind source separation (BSS) method, called information geometric blind source separation (IGBSS).
Bias-Variance Trade-Off in Hierarchical Probabilistic Models Using Higher-Order Feature Interactions
However, it is well known that increasing the number of parameters also increases the complexity of the model which leads to a bias-variance trade-off.
