Statistical Learning
PromptRestorer: A Prompting Image Restoration Method with Degradation Perception Cong Wang
Image restoration aims to recover clear high-quality images from given degraded ones.
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
In a seminal paper, Szegedy et al. [Sze+14] observed that deep networks are extremely vulnerable to adversarial examples, namely, very small perturbations to the inputs
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
In a seminal paper, Szegedy et al. [Sze+14] observed that deep networks are extremely vulnerable to adversarial examples, namely, very small perturbations to the inputs
NavigatingtheEffectofParametrization forDimensionalityReduction
Parametric dimensionality reduction methods have gained prominence for their ability togeneralize tounseen datasets, anadvantage that traditional approaches typically lack. Despite their growing popularity, there remains a prevalent misconception among practitioners about the equivalence in performance between parametric and non-parametric methods. Here, we showthat these methods are not equivalent - parametric methods retain global structure but lose significant localdetails.
DifferentiableLearningUnderTriage
In recent years, there has been a raising interest on a new learning paradigm which seeks the development of predictive models that operate under different automation levels--models that take decisions for a given fraction of instances and leave the remaining ones to human experts.
