Oceania
GAVEL: Generating Games Via Evolution and Language Models Graham T odd New York University Tandon Brooklyn, New York, USA gdrtodd Alexander G. Padula ETH Zurich Zurich, Switzerland apadula
Automatically generating novel and interesting games is a complex task.
TowardsData-AlgorithmDependentGeneralization: aCaseStudyonOverparameterizedLinearRegression
In many scenarios, this failure can be attributed to obscuring the crucial interplay between the training algorithm and the underlying data distribution.
Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective Zihan Luo
GNNs to mitigate the bias as well as boost their utility in an end-to-end manner.
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
With high-dimensional state spaces, visual reinforcement learning (RL) faces significant challenges in exploitation and exploration, resulting in low sample efficiency and training stability.
Debiasing Conditional Stochastic Optimization Lie He
The sample-averaged gradient of the CSO objective is biased due to its nested structure, and therefore requires a high sample complexity for convergence. We introduce a general stochastic extrapolation technique that effectively reduces the bias.
All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation Liyao T ang
This approach may, however, hinder the comprehensive exploitation of unlabeled data points. We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly.