arXiv Machine Learning By Ashkan Soleymani, Gabriele Farina

A Quasipolynomial Algorithm for $\ell_\infty$ Contractions

Read the original on arXiv Machine Learning →

The paper presents a quasipolynomial-time algorithm for finding an ε-approximate fixed point of any d-dimensional nonexpansion under the λ∞ norm, running in time −log(1/ε)^{O(log^2 d)}. The method relies on a boosting argument that geometrically shrinks the search region. As a consequence, the algorithm shows that simple stochastic games can be solved in quasipolynomial time.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Sep 17

Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency and Nearly Optimal Oracle Rates

We study efficient algorithms for realizing the first-order oracle complexity of optimization of $G$-Lipschitz convex functions with respect to the $\ell_{q}$-norm over an $\ell_{p}$-ball of radius $R$, where $1\leq p,q\leq \infty$. For $p<q$, we obtain error $\widetilde{O}_{p,q}(GR/T^{1/p-(1/q-1/2)_{+}})$ after $T$ oracle queries, efficiently realizing the nearly optimal rates of (MBG+26), thereby resolving the nonsmooth end of the COLT 2015 open problem (Guz15b).