2 citations · 2 across the 6 of their papers we have counts for
7 papers · 1 filter
Does Compression Imply Generalization? A Minimum Description Length Perspective
Lincen Yang, Jiayang Shi, Nan Pu +4
A central question in modern learning theory is what notion of compression, if any, explains why over-parameterized neural networks generalize. Existing answers measure complexity…
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Zhao Yang, Yuxuan Jiang, Ting-Chih Chen +18
Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate current pipelines, PPO and GRPO, represent only a narrow slice of what RL offers.…
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders
Rogelio A Mancisidor, Robert Jenssen, Shujian Yu +1
Multimodal learning with variational autoencoders (VAEs) requires estimating joint distributions to evaluate the evidence lower bound (ELBO). Current methods, the product and mixtu…
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
Hongming Li, Zhao Yang, Shujian Yu +3
Reinforcement learning agents depend on reward signals whose density is rarely under the designer's control, and when such signals are absent, an agent must generate its own drive…
Generalized Cauchy-Schwarz Divergence and Its Deep Learning Applications
Mingfei Lu, Chenxu Li, Shujian Yu +2
Divergence measures play a central role and become increasingly essential in deep learning, yet efficient measures for multiple (more than two) distributions are rarely explored. T…
Domain Adaptation with Cauchy-Schwarz Divergence
Wenzhe Yin, Shujian Yu, Yicong Lin +3
Domain adaptation aims to use training data from one or multiple source domains to learn a hypothesis that can be generalized to a different, but related, target domain. As such, h…
Cauchy-Schwarz Divergence Information Bottleneck for Regression
Shujian Yu, Xi Yu, Sigurd Løkse +2
The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum suf…