Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling
Mengyu Li, Qianqian Qu, Jun S. Liu
Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reused as a prior and combined wi…
cs.LG2024
Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories
Yicheng Li, Haobo Zhang, Jianfa Lai +2
A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the complexity of their training dynamic…