5 papers · 1 filter
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
Jiashun Liu, Zihao Wu, Johan Obando-Ceron +3
Deep reinforcement learning (RL) agents frequently suffer from neuronal activity loss, which impairs their ability to adapt to new data and learn continually. A common method to qu…
Teleportation With Null Space Gradient Projection for Optimization Acceleration
Zihao Wu, Juncheng Dong, Ahmed Aloui +1
Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale. In particular, teleportation has emerged as a promising approach,…
S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting
Zihao Wu, Juncheng Dong, Haoming Yang +1
Time series forecasting has recently achieved significant progress with multi-scale models to address the heterogeneity between long and short range patterns. Despite their state-o…
Score-Based Metropolis-Hastings Algorithms
Ahmed Aloui, Ali Hasan, Juncheng Dong +2
In this paper, we introduce a new approach for integrating score-based models with the Metropolis-Hastings algorithm. While traditional score-based diffusion models excel in accura…
Offline Stochastic Optimization of Black-Box Objective Functions
Juncheng Dong, Zihao Wu, Hamid Jafarkhani +2
Many challenges in science and engineering, such as drug discovery and communication network design, involve optimizing complex and expensive black-box functions across vast search…