activity
20182024
most citedLearning Cross-Scale Weighted Prediction for Efficient Neural Video Compression

31 citations · 125 across the 25 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2023★ 1 cited

When and Why Momentum Accelerates SGD:An Empirical Study

Jingwen Fu, Bohan Wang, Huishuai Zhang +3

Momentum has become a crucial component in deep learning optimizers, necessitating a comprehensive understanding of when and why it accelerates stochastic gradient descent (SGD). T…

cs.LG2023

Learning Trajectories are Generalization Indicators

Jingwen Fu, Zhizheng Zhang, Dacheng Yin +2

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient des…

cs.LG2023★ 1 cited

Versatile Neural Processes for Learning Implicit Neural Representations

Zongyu Guo, Cuiling Lan, Zhizheng Zhang +2

Representing a signal as a continuous function parameterized by neural network (a.k.a. Implicit Neural Representations, INRs) has attracted increasing attention in recent years. Ne…

cs.LG2022★ 21 cited

Mask-based Latent Reconstruction for Reinforcement Learning

Tao Yu, Zhizheng Zhang, Cuiling Lan +2

For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance. However, in practice, limited experience and h…

cs.LG2021★ 1 cited

Confounder Identification-free Causal Visual Feature Learning

Xin Li, Zhizheng Zhang, Guoqiang Wei +4

Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free o…

cs.LG2019★ 2 cited

Asynchronous Episodic Deep Deterministic Policy Gradient: Towards Continuous Control in Computationally Complex Environments

Zhizheng Zhang, Jiale Chen, Zhibo Chen +1

Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from da…