Testing Learning--Reasoning Correspondence as a Sample-Efficient Inductive Bias for Small Reasoning Agents
Imported research from GitHub repository run-e0dc977c-4dbd-405d-b408-b63e16fc7fb3.
Home / Search
Imported research from GitHub repository run-e0dc977c-4dbd-405d-b408-b63e16fc7fb3.
Imported research from GitHub repository run-ae469554-95e8-48b3-b5b7-9605333b88c0.
Imported research from GitHub repository run-a7b820ba-0109-4032-a46f-2bd30e4fe321.
Autonomous research run a3f2607f (omegaXiv / quarks engine).
Imported research from GitHub repository run-a0c76985-7e4b-4426-b755-e36495b12d4d.
We study whether sublinear {Nystr\"om} sampling preserves the spectral gap of the symmetric normalized graph Laplacian. For a finite undirected graph with positive degrees, we work…
Randomized SVD is often run with a fixed oversampling parameter, even though approximation quality is driven by the spectrum and by the power-iteration count. We test whether the s…
Parameter averaging is often used as a cheap way to smooth stochastic optimization trajectories, and a natural hypothesis is that the averaging horizon should grow as a cosine lear…