Timezone: »
We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that achieves jointly the optimal prediction error rates for least-squares regression, both in terms of forgetting of initial conditions in O(1/n^2), and in terms of dependence on the noise and dimension d of the problem, as O(d/n). Our new algorithm is based on averaged accelerated regularized gradient descent, and may also be analyzed through finer assumptions on initial conditions and the Hessian matrix, leading to dimension-free quantities that may still be small while the "optimal " terms above are large. In order to characterize the tightness of these new bounds, we consider an application to non-parametric regression and use the known lower bounds on the statistical performance (without computational limits), which happen to match our bounds obtained from a single pass on the data and thus show optimality of our algorithm in a wide variety of particular trade-offs between bias and variance. [joint work with Aymeric Dieuleveut and Nicolas Flammarion]
Author Information
Francis Bach (INRIA - Ecole Normale Superieure)
Francis Bach is a researcher at INRIA, leading since 2011 the SIERRA project-team, which is part of the Computer Science Department at Ecole Normale Supérieure in Paris, France. After completing his Ph.D. in Computer Science at U.C. Berkeley, he spent two years at Ecole des Mines, and joined INRIA and Ecole Normale Supérieure in 2007. He is interested in statistical machine learning, and especially in convex optimization, combinatorial optimization, sparse methods, kernel-based learning, vision and signal processing. He gave numerous courses on optimization in the last few years in summer schools. He has been program co-chair for the International Conference on Machine Learning in 2015.
More from the Same Authors
-
2020 : Francis Bach - Where is Machine Learning Going? »
Francis Bach -
2017 : Concluding remarks »
Francis Bach · Benjamin Guedj · Pascal Germain -
2017 : Neil Lawrence, Francis Bach and François Laviolette »
Neil Lawrence · Francis Bach · Francois Laviolette -
2017 : Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance »
Francis Bach -
2017 : Overture »
Benjamin Guedj · Francis Bach · Pascal Germain -
2017 Workshop: (Almost) 50 shades of Bayesian Learning: PAC-Bayesian trends and insights »
Benjamin Guedj · Pascal Germain · Francis Bach -
2017 Poster: On Structured Prediction Theory with Calibrated Convex Surrogate Losses »
Anton Osokin · Francis Bach · Simon Lacoste-Julien -
2017 Oral: On Structured Prediction Theory with Calibrated Convex Surrogate Losses »
Anton Osokin · Francis Bach · Simon Lacoste-Julien -
2017 Poster: Nonlinear Acceleration of Stochastic Algorithms »
Damien Scieur · Francis Bach · Alexandre d'Aspremont -
2017 Poster: Integration Methods and Optimization Algorithms »
Damien Scieur · Vincent Roulet · Francis Bach · Alexandre d'Aspremont -
2016 : Submodular Functions: from Discrete to Continuous Domains »
Francis Bach -
2016 Tutorial: Large-Scale Optimization: Beyond Stochastic Gradient Descent and Convexity »
Suvrit Sra · Francis Bach