1 citations · 1 across the 8 of their papers we have counts for
6 papers · 1 filter
How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL
Qifu Wen, Shuaijun Liu, Zihan Zhou +2
Accurate posterior prediction need not require accurate approximation of Bayesian updates. We prove that an unbounded gap between the update maps can coexist with vanishing predict…
Gradient Under Microscope: Benchmarking Resource Utilization of Memory-Efficient Gradient Computation Methods
Sarthak Mahapatra, Zihan Zhou, Khatoon Khedri +2
AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training on constrained hardware. We b…
Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching
Chenguang Wang, Zihan Zhou, Lei Bai +1
Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches rely on rigid reaction libraries…
Unrewarded Exploration in Large Language Models Reveals Latent Learning from Psychology
Jian Xiong, Jingbo Zhou, Zihan Zhou +6
Latent learning, classically theorized by Tolman, shows that biological agents (e.g., rats) can acquire internal representations of their environment without rewards, enabling rapi…
GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping
Qifu Wen, Xi Zeng, Zihan Zhou +4
Early stopping monitors global validation loss and halts all parameter updates simultaneously, which is computationally costly for large transformers due to the extended time requi…
Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs
Zihan Zhou, Honghao Wei, Lei Ying
This paper considers the best policy identification (BPI) problem in online Constrained Markov Decision Processes (CMDPs). We are interested in algorithms that are model-free, have…