paper-with-me

홈 › Papers

The importance of better models in stochastic optimization

2019-03-20 · Hilal Asi, John C. Duchi

Standard stochastic optimization methods are brittle, sensitive to stepsize choices and other algorithmic parameters, and they exhibit instability outside of well-behaved families of objectives. To address these challenges, we investigate models for stochastic minimization and learning problems that exhibit better robustness to problem families and algorithmic parameters. With appropriately accurate models---which we call the aProx family---stochastic methods can be made stable, provably convergent and asymptotically optimal; even modeling that the objective is nonnegative is sufficient for this stability. We extend these results beyond convexity to weakly convex objectives, which include compositions of convex losses with smooth functions common in modern machine learning applications. We highlight the importance of robustness and accurate modeling with a careful experimental evaluation of convergence time and algorithm sensitivity.

📄 PDF Abstract BibTeX arXiv:1903.08619

Code (1)

HilalAsi/APROX-Robust-Stochastic-Optimization-Algorithms pytorch

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Stochastic Optimization with Importance Sampling

2014-01-13 · Peilin Zhao, Tong Zhang

Uniform sampling of training data has been commonly used in traditional stochastic optimization algorithms such as Proximal Stochastic Gradient Descent (prox-SGD) and Proximal Stochastic Dual Coordinate Ascent (prox-SDCA…

Stochastic Optimization

Reliable uncertainty estimate for antibiotic resistance classification with Stochastic Gradient Langevin Dynamics

2018-11-27 · Md-Nafiz Hamid, Iddo Friedberg

Antibiotic resistance monitoring is of paramount importance in the face of this on-going global epidemic. Deep learning models trained with traditional optimization algorithms (e.g. Adam, SGD) provide poor posterior esti…

Deep LearningGeneral Classification

Biased Importance Sampling for Deep Neural Network Training

2017-05-31 · Angelos Katharopoulos, François Fleuret

Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learni…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+1

Train faster, generalize better: Stability of stochastic gradient descent

2015-09-03 · Moritz Hardt, Benjamin Recht, Yoram Singer

We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is algorithmically stable in the sense of Bou…

Safe Adaptive Importance Sampling

2017-11-07 · NeurIPS 2017 12 · Sebastian U. Stich, Anant Raj, Martin Jaggi

Importance sampling has become an indispensable strategy to speed up optimization algorithms for large-scale applications. Improved adaptive variants - using importance values defined by the complete gradient information…