9 papers
Sharp proper estimation of fixed-component Gaussian location mixtures in polynomial time
Hengzhi He, Guang Cheng
We consider a mixture of at most unit-covariance Gaussians in whose means belong to a fixed-radius ball, with no separation or minimum-weight condition. Doss, Wu…
Tensor-normal maximum likelihood estimation at the operator-norm sample threshold
Hengzhi He, Guang Cheng
Let be independent Gaussian tensors in with a common covariance matrix given by the Kronecker product of …
Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework
Hengzhi He, Shirong Xu, Guang Cheng
Recent studies identified an intriguing phenomenon in recursive generative model training known as model collapse, where models trained on data generated by previous models exhibit…
Enhancing Table Reasoning with Deterministic Table-State Rewards
Tung Sum Thomas Kwok, Xinyu Wang, Hengzhi He +9
Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for intermediate reasoning states. Ex…
Let the Target Select for Itself: Data Selection via Target-Aligned Paths
Huitao Yang, Hengzhi He, Guang Cheng
Targeted data selection aims to identify training samples from a large candidate pool that improve performance on a specific downstream task. Many recent methods estimate candidate…
"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihood
Peiyu Yu, Dinghuai Zhang, Hengzhi He +10
Noise Contrastive Estimation (NCE) has fueled major breakthroughs in representation learning and generative modeling. Yet a long-standing challenge remains: accurately estimating r…