Search Results for author:
Found 6 papers, 2 papers with code
Implicit Manifold Learning on Generative Adversarial Networks
This paper raises an implicit manifold learning perspective in Generative Adversarial Networks (GANs), by studying how the support of the learned distribution, modelled as a submanifold $\mathcal{M}_{\theta}$, perfectly match with $\mathcal{M}_{r}$, the support of the real data distribution.
Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds
In this paper, we investigate Dimensionality reduction (DR) maps in an information retrieval setting from a quantitative topology point of view.
MMA Training: Direct Input Space Margin Maximization through Adversarial Training
We study adversarial robustness of neural networks from a margin maximization perspective, where margins are defined as the distances from inputs to a classifier's decision boundary.
On the Sensitivity of Adversarial Robustness to Input Data Distributions
Even a semantics-preserving transformations on the input data distribution can cause a significantly different robustness for the adversarial trained model that is both trained and evaluated on the new distribution.
Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets
Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and costly exploration.
Rethinking Test-time Likelihood: The Likelihood Path Principle and Its Application to OOD Detection
Second, introducing new theoretic tools such as nearly essential support, essential distance and co-Lipschitzness, we obtain non-asymptotic provable OOD detection guarantees for certain distillation of the minimal sufficient statistics.
