no code implementations • 31 Jul 2023 • Matthew Streeter
Majorization-minimization (MM) is a family of optimization methods that iteratively reduce a loss by minimizing a locally-tight upper bound, called a majorizer.
1 code implementation • 22 Dec 2022 • Matthew Streeter, Joshua V. Dillon
We then recursively combine the bounds for the elementary functions using an interval arithmetic variant of Taylor-mode automatic differentiation.
no code implementations • 30 Nov 2022 • Andreas Döpp, Christoph Eberle, Sunny Howard, Faran Irshad, Jinpu Lin, Matthew Streeter
Laser-plasma physics has developed rapidly over the past few decades as high-power lasers have become both increasingly powerful and more widely available.
no code implementations • 28 Jun 2019 • Matthew Streeter
We consider the problem of learning a loss function which, when minimized over a training dataset, yields a model that approximately minimizes a validation error metric.
no code implementations • 21 Feb 2019 • Matthew Streeter
We derive an optimal policy for adaptively restarting a randomized algorithm, based on observed features of the run-so-far, so as to minimize the expected time required for the algorithm to successfully terminate.
no code implementations • 19 Feb 2019 • Matthew Streeter
We present algorithms for efficiently learning regularizers that improve generalization.
no code implementations • ICML 2018 • Matthew Streeter
We present an approximation algorithm that takes a pool of pre-trained models as input and produces from it a cascaded model with similar accuracy but lower average-case cost.
no code implementations • NeurIPS 2014 • Brendan Mcmahan, Matthew Streeter
We analyze new online gradient descent algorithms for distributed systems with large delays between gradient computations and the corresponding updates.
no code implementations • 3 Jul 2014 • Daniel Golovin, Andreas Krause, Matthew Streeter
How should we dynamically rank information sources to maximize the value of the ranking?
no code implementations • NeurIPS 2012 • Brendan Mcmahan, Matthew Streeter
We present an algorithm that, without such prior knowledge, offers near-optimal regret bounds with respect to _any_ choice of x*.
no code implementations • NeurIPS 2009 • Matthew Streeter, Daniel Golovin, Andreas Krause
Which ads should we display in sponsored search in order to maximize our revenue?
no code implementations • NeurIPS 2008 • Matthew Streeter, Daniel Golovin
We present an algorithm for solving a broad class of online resource allocation problems.