Statistical Learning
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
We revisit data selection in a modern context of finetuning from a fundamental perspective.
Efficient Symmetric Norm Regression via Linear Sketching
Zhao Song, Ruosong Wang, Lin Yang, Hongyang Zhang, Peilin Zhong
Neural Information Processing Systems http://nips.cc/
ed7b8e1312f6ba8af6e4316dcd28bb3d-Paper-Conference.pdf
Wefindalarge range of behavior that can be precisely characterized by a new measure ofconfounding strength.
Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse
James Lucas, George Tucker, Roger B. Grosse, Mohammad Norouzi
Neural Information Processing Systems http://nips.cc/
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo
Marton Havasi, Josรฉ Miguel Hernรกndez-Lobato, Juan Josรฉ Murillo-Fuentes
The best-fit Gaussian distribution is denoted with adashed line.
Revisit last-iterate convergence of mSGD under milder requirement on step size
Understanding convergence of stochastic gradient descent (SGD) based optimization algorithms can help deal with enormous machine learning problems.
