Statistical Learning
Supplement to " Kernel-based tests for Likelihood-Free Hypothesis Testing " Patrik Róbert Gerber
As mentioned in the discussion succeeding Corollary 3.6, we do conjecture the tight
Kernel-Based Tests for Likelihood-Free Hypothesis Testing
Despite empirical advances, the theoretical study of frequentist LFI is still in its infancy.
Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion Junliang Li1, 2, Y ajun Y ang
Trending topic diffusion and prediction analysis is an important problem and has been well studied in social networks.
Optimal Exploration for Model-Based RL in Nonlinear Systems Andrew Wagenmaker Paul G. Allen School of Computer Science & Engineering University of Washington Seattle, W A98195 Guanya Shi
Learning to control unknown nonlinear dynamical systems is a fundamental problem in reinforcement learning and control theory.
A Metadata-Driven Approach to Understand Graph Neural Networks
GNN architecture that is universally effective across a wide range of graph machine learning tasks.
ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training Antonio Norelli Marco Fumero
Furthermore, our model has unique properties.
Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction Tao Fang
CLIP model to map the training data to a compact feature representation, which essentially extends the sparse semantics of training data to dense ones, thus alleviating the semantic gap of the instances nearby known concepts (i.e., inside the
A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm
Unlike the conventional machine learning paradigms where learning is performed on a static dataset, domain incremental learning, i.e., continual learning with evolving domains, hopes to accommodate the model to the dynamically changing data distributions, while retaining the knowledge learned from previous domains [