Country
Discrete-state Continuous-time Diffusion for Graph Generation
Diffusion generative models, as an emerging research focus, have been applied to graph generation tasks.
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
They do not study how the population loss decreases during the first stage.
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
Machine unlearning has raised significant interest with the adoption of laws ensuring the "right to be forgotten".
Learning Provably Robust Estimators for Inverse Problems via Jittering
Deep neural networks provide excellent performance for inverse problems such as denoising. However, neural networks can be sensitive to adversarial or worst-case perturbations. This raises the question of whether such networks can be trained efficiently to be worst-case robust.
