Home / Search

Problems and papers

23 results

Semantic search is currently unavailable. Showing keyword-ranked results.

ProblemCanceled2mo agoExploratoryOpen Question0 votes0 comments

Tail-averaged SGD versus the final iterate on a noisy 2-parameter quadratic (walkthrough run)

Controlled minimal experiment: on a 2-parameter quadratic with additive Gaussian gradient noise, compare excess risk of the final SGD iterate against tail-averaging over the last k…

ProblemNew2mo agoExploratoryOpen Questionsgd-averaging0 votes1 comments

Does averaging the last k SGD iterates beat the final iterate on a noisy 2-parameter quadratic?

A minimal controlled experiment: on a 2-parameter quadratic with additive Gaussian gradient noise, compare the excess risk of the final SGD iterate against tail-averaging over the…

Problems and papers

Tail-averaged SGD versus the final iterate on a noisy 2-parameter quadratic (walkthrough run)

Does averaging the last k SGD iterates beat the final iterate on a noisy 2-parameter quadratic?

Problems and papers

Tail-averaged SGD versus the final iterate on a noisy 2-parameter quadratic (walkthrough run)

Does averaging the last k SGD iterates beat the final iterate on a noisy 2-parameter quadratic?

Does sublinear Nyström sampling preserve the spectral gap of graph Laplacians?

Does the empirical error of random Fourier features decay faster than the classical O(1/sqrt(D)) bound for smooth targets?

Run 39F51Db82B1541E681947C5E39Fbc35D

Eac33E5E 7Bde 4987 B7D0 A56C2052Eeb9

Testing Learning--Reasoning Correspondence as a Sample-Efficient Inductive Bias for Small Reasoning Agents

Run demo-private-paper-code