Our ideas also can be applied to the more general setting that the objective function only satisfies PL condition for one variable.

Unobserved discrete data are ubiquitous in many scientific disciplines, and how to learn the causal structure of these latent variables is crucial for uncovering data patterns. Most studies focus on the linear latent variable model or impose strict constraints on latent structures, which fail to address cases in discrete data involving non-linear relationships or complex latent structures.

Previous works attempting to close this gap have failed to fully investigate the exponentially growing number of feature combinations which deep networks consider automatically during training. In this work, we develop a tractable selection algorithm to efficiently identify the necessary feature combinations byleveraging techniques infeature interaction detection. Our proposed Sparse Interaction AdditiveNetworks (SIAN) construct abridge from thesesimple andinterpretable models tofullyconnected neuralnetworks.

The PETL parameters are trained only on Task 1 (the'first-session') of a set of

Research efforts on learning implicit 3D shapes without 3D supervision have primarily resorted to binary occupancy[26,34]asthe representation, aiming tomatch reprojected 3D occupancytothe given binary masks. Current worksadopting signed distance functions (SDF) either require apretrained deep shape prior [27] or are limited to discretized representations [14] that do not scale up with resolution.