Arxiv_icml
A couple of exiting projects I have been working for the past year are finally out on arXiv. Check them out!
- Theoretical characterization of uncertainty in high-dimensional linear classification
- Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks
- Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension
- Error Rates for Kernel Classification under Source and Capacity Conditions
- Bayesian Inference with Nonlinear Generative Models: Comments on Secure Learning
Enjoy Reading This Article?
Here are some more articles you might like to read next: