72 citations · 173 across the 16 of their papers we have counts for
6 papers · 1 filter
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
Mingyuan Zhou, Huangjie Zheng, Zhendong Wang +2
We introduce Score identity Distillation (SiD), an innovative data-free method that distills the generative capabilities of pretrained diffusion models into a single-step generator…
Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping
Russell Z. Kunes, Mingzhang Yin, Max Land +3
Gradient estimation is often necessary for fitting generative models with discrete latent variables, in contexts such as reinforcement learning and variational autoencoder (VAE) tr…
Partial Identification with Noisy Covariates: A Robust Optimization Approach
Wenshuo Guo, Mingzhang Yin, Yixin Wang +1
Causal inference from observational datasets often relies on measuring and adjusting for covariates. In practice, measurements of the covariates can often be noisy and/or biased, o…
Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator
Siamak Zamani Dadaneh, Shahin Boluki, Mingzhang Yin +2
Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders…
Meta-Learning without Memorization
Mingzhang Yin, George Tucker, Mingyuan Zhou +2
The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged a…
Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy
Yunhao Tang, Mingzhang Yin, Mingyuan Zhou
Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) polic…