Statistical Learning
Unraveling the Gradient Descent Dynamics of Transformers
By analyzing the loss landscape of a single Transformer layer using Softmax and Gaussian attention kernels, our work provides concrete answers to these questions.
Intrinsic Self-Supervision for Data Quality Audits
Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance.
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Tai-Jiang Mu is the corresponding author.
A Kernel Perspective on Distillation-based Collaborative Learning
To tackle this problem, we rigorously analyze a representative distillation-based algorithm in the view of kernel regression.
Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree
Point cloud registration is a crucial task in 3D computer vision that involves aligning a pair of partially overlapped point clouds to create a unified scene representation.
Learning Structured Representations with Hyperbolic Embeddings
Most real-world datasets consist of a natural hierarchy between classes or an inherent label structure that is either already available or can be constructed cheaply. However, most existing representation learning methods ignore this hierarchy, treating labels as permutation invariant.
