South America
A Quantitative Geometric Approach to Neural-Network Smoothness
We implement the algorithms induced from this quantitative geometric approach, which are based on semidefinite programming (SDP).
A Unifying Framework for Online Optimization with Long-Term Constraints Matteo Castiglioni Politecnico di Milano Andrea Celli Bocconi University Alberto Marchesi Politecnico di Milano Giulia Romano
Our framework employs traditional regret minimizers as black-box components.
A Unifying Framework for Online Optimization with Long-Term Constraints Matteo Castiglioni Politecnico di Milano Andrea Celli Bocconi University Alberto Marchesi Politecnico di Milano Giulia Romano
Our framework employs traditional regret minimizers as black-box components.
Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
Specifically, we introduce Multiway Transformer, where each block contains a pool of modality-specific experts and a shared self-attention layer.
Coresets for Decision Trees of Signals
If the labels are given from a discrete set, the trees are usually called classification trees, and otherwise they are usually called regression trees .
Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks
The graph retrieval problem is to search in a large corpus of graphs for ones that are most similar to a query graph.
Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations
To account also for spatial dependencies, Cini et al.