Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Roberts, Lindon"'
Autor:
Aminzadeh, Alaleh, Kingston, Andrew M., Roberts, Lindon, Paganin, David M., Petersen, Timothy C., Svalbe, Imants D.
Scanning objects with a more tightly focused beam (for example of photons or electrons) can provide higher-resolution images. However the stronger localisation of energy deposition can damage tissues in organic samples or may rearrange the chemical s
Externí odkaz:
http://arxiv.org/abs/2410.18348
We consider the problem of optimizing the sum of a smooth, nonconvex function for which derivatives are unavailable, and a convex, nonsmooth function with easy-to-evaluate proximal operator. Of particular focus is the case where the smooth part has a
Externí odkaz:
http://arxiv.org/abs/2407.14915
Autor:
Roberts, Lindon
We develop a new approximation theory for linear and quadratic interpolation models, suitable for use in convex-constrained derivative-free optimization (DFO). Most existing model-based DFO methods for constrained problems assume the ability to const
Externí odkaz:
http://arxiv.org/abs/2403.14960
The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning process to appropriately calibrate a stepsize for a given problem. In thi
Externí odkaz:
http://arxiv.org/abs/2311.08615
Various tasks in data science are modeled utilizing the variational regularization approach, where manually selecting regularization parameters presents a challenge. The difficulty gets exacerbated when employing regularizers involving a large number
Externí odkaz:
http://arxiv.org/abs/2308.10098
Derivative-free algorithms seek the minimum of a given function based only on function values queried at appropriate points. Although these methods are widely used in practice, their performance is known to worsen as the problem dimension increases.
Externí odkaz:
http://arxiv.org/abs/2308.04734
Autor:
Ehrhardt, Matthias J., Roberts, Lindon
Estimating hyperparameters has been a long-standing problem in machine learning. We consider the case where the task at hand is modeled as the solution to an optimization problem. Here the exact gradient with respect to the hyperparameters cannot be
Externí odkaz:
http://arxiv.org/abs/2301.04764
Autor:
Kingston, Andrew M., Roberts, Lindon, Aminzadeh, Alaleh, Pelliccia, Daniele, Svalbe, Imants D., Paganin, David M.
Publikováno v:
Physical Review A 107, 023524 (2023)
Classical ghost imaging is a new paradigm in imaging where the image of an object is not measured directly with a pixelated detector. Rather, the object is subject to a set of illumination patterns and the total interaction of the object, e.g., refle
Externí odkaz:
http://arxiv.org/abs/2211.03792
Autor:
Roberts, Lindon, Smyth, Edward
Publikováno v:
EURO Journal on Computational Optimization, vol 10 (2022)
In distributed learning, a central server trains a model according to updates provided by nodes holding local data samples. In the presence of one or more malicious servers sending incorrect information (a Byzantine adversary), standard algorithms fo
Externí odkaz:
http://arxiv.org/abs/2208.11879
Autor:
Roberts, Lindon, Royer, Clément W.
In this paper, we study a generic direct-search algorithm in which the polling directions are defined using random subspaces. Complexity guarantees for such an approach are derived thanks to probabilistic properties related to both the subspaces and
Externí odkaz:
http://arxiv.org/abs/2204.01275