Asia
Many-body Approximation for Non-negative Tensors
We present an alternative approach to decompose non-negative tensors, called many-body approximation .
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
While agents' learning is data-driven, sampling from millions
State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memory
State-space models have gained popularity in sequence modelling due to their simple and efficient network structures. However, the absence of nonlinear activation along the temporal direction limits the model's capacity.
Estimating Riemannian Metric with Noise-Contaminated Intrinsic Distance
The key quantity of interest here is the Riemannian metric, which characterizes the Riemannian geometry and defines straight lines and derivatives on the manifold.
Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts.
Squared Neural Families: A New Class of Tractable Density Models Russell Tsuchida
Probabilistic modelling lies at the heart of machine learning.
CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts
Data-driven models learned often struggle to generalize due to widespread subpopulation shifts, especially the presence of both spurious correlations and group imbalance (SC-GI).