Education
Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the loss compared to an oblivious one? To what extent can a randomized learner reduce the loss compared to a deterministic one?
UV-free Texture Generation with Denoising and Geodesic Heat Diffusions Simone Foti Stefanos Zafeiriou T olga Birdal Department of Computing Imperial College London
Meshes are surface discretisations intentionally designed to represent the geometry of 3D objects.
HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning Lu Bai
Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning.
Parseval Regularization for Continual Reinforcement Learning
We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks.
Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions
A common practice to address this issue is using the model itself to annotate unlabeled data samples.
