Search Results for author:
Found 11 papers, 3 papers with code
Semi-supervised Adversarial Learning for Complementary Item Recommendation
In this work, we propose a novel approach that can leverage both item side-information and labeled complementary item pairs to generate effective complementary recommendations for cold items, i. e., for items for which no co-purchase statistics yet exist.
Collaborative Image Understanding
A series of experiments on datasets from e-commerce and social media demonstrates that considering collaborative signals helps to significantly improve the performance of the main task of image classification by up to 9. 1%.
Beyond Ridge Regression for Distribution-Free Data
In the context of online prediction where the min-max solution is the Normalized Maximum Likelihood (NML), it has been suggested to use NML with ``luckiness'': A prior-like function is applied to the hypothesis class, which reduces its effective size.
Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection
Furthermore, we describe how to efficiently apply the derived pNML regret to any pretrained deep NN, by employing the explicit pNML for the last layer, followed by the softmax function.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustness
Specifically, our defense performs adversarial targeted attacks according to different hypotheses, where each hypothesis assumes a specific label for the test sample.
Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression
Modern machine learning models do not obey this paradigm: They produce an accurate prediction even with a perfect fit to the training set.
Learning Rotation Invariant Features for Cryogenic Electron Microscopy Image Reconstruction
A fundamental step in the recovering of the 3D single-particle structure is to align its 2D projections; thus, the construction of a canonical representation with a fixed rotation angle is required.
Balancing Specialization, Generalization, and Compression for Detection and Tracking
To this end, we propose a novel loss that balances compression and acceleration of a deep learning model vs. loss of generalization capabilities.
Universal Learning Approach for Adversarial Defense
In particular, we follow the recently suggested Predictive Normalized Maximum Likelihood (pNML) scheme for universal learning, whose goal is to optimally compete with a reference learner that knows the true label of the test sample but is restricted to use a learner from a given hypothesis class.
A New Look at an Old Problem: A Universal Learning Approach to Linear Regression
Linear regression is a classical paradigm in statistics.
Deep pNML: Predictive Normalized Maximum Likelihood for Deep Neural Networks
Finally, we extend the pNML to a ``twice universal'' solution, that provides universality for model class selection and generates a learner competing with the best one from all model classes.
