1 citations · 3 across the 17 of their papers we have counts for
5 papers · 1 filter
Dynamical Behaviors of the Gradient Flows for In-Context Learning
Songtao Lu, Yingdong Lu, Tomasz Nowicki
We derive the system of differential equations for the gradient flow characterizing the training process of linear in-context learning in full generality. Next, we explore the geom…
On The Variance of Schatten -Norm Estimation with Gaussian Sketching Matrices
Lior Horesh, Vasileios Kalantzis, Yingdong Lu +1
Monte Carlo matrix trace estimation is a popular randomized technique to estimate the trace of implicitly-defined matrices via averaging quadratic forms across several observations…
On the iterations of some random functions with Lipschitz number one
Yingdong Lu, Tomasz Nowicki
For the iterations of random functions with Lipschitz number one, we represent the dynamics as a Markov chain and prove its convergence under mild conditions. We a…
Regenerative Ulam-von Neumann Algorithm: An Innovative Markov chain Monte Carlo Method for Matrix Inversion
Soumyadip Ghosh, Lior Horesh, Vassilis Kalantzis +2
This paper presents a regenerative variant of the classical Ulam-von Neumann Markov chain Monte Carlo algorithm for the approximation of the matrix inverse. The algorithm presented…
On Convergence of the Alternating Directions SGHMC Algorithm
Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki
We study convergence rates of Hamiltonian Monte Carlo (HMC) algorithms with leapfrog integration under mild conditions on stochastic gradient oracle for the target distribution (SG…