Statistical Learning
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
Ideally, the obtained unlearnability can prevent algorithms from training usable models.
Generative Retrieval Meets Multi-Graded Relevance Y ubao T ang
Generative retrieval represents a novel approach to information retrieval.
Accelerating ERM for data-driven algorithm design using output-sensitive techniques
Data-driven algorithm design is a promising, learning-based approach for beyond worst-case analysis of algorithms with tunable parameters. An important open problem is the design of computationally efficient data-driven algorithms for combinatorial algorithm families with multiple parameters.
TabEBM: AT abular Data Augmentation Method with Distinct Class-Specific Energy-Based Models
Figure 1: Evaluation of T abEBM and other state-of-the-art tabular generative methods across six key metrics (larger area indicates better performance).