1. Unbiased Gradient Estimation In Unrolled Computation Graphs With Persistent Evolution
: propose persistent evolution strategies(PES)
2. Oops I took a gradient: Scalable sampling for discrete distributions
3. Optimal complexity in decentralised training
4. Understanding self-supervised learning dynamics without contrastive pairs
5. Solving high-dimensional parabolic PDEs using the tensor train format
NLP Researcher : https://hyukhunkoh-ai.github.io/