Statistical Perspective of Top-K Sparse Softmax Gating Mixture of
ExpertsInternational Conference on Learning Representations (ICLR), 2023 |
Towards Convergence Rates for Parameter Estimation in Gaussian-gated
Mixture of ExpertsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
On Excess Mass Behavior in Gaussian Mixture Models with
Orlicz-Wasserstein DistancesInternational Conference on Machine Learning (ICML), 2023 |
Refined Convergence Rates for Maximum Likelihood Estimation under Finite
Mixture ModelsInternational Conference on Machine Learning (ICML), 2022 |
Learning latent causal graphs via mixture oraclesNeural Information Processing Systems (NeurIPS), 2021 |