How to iron out rough landscapes and get optimal performances: Replicated Gradient Descent and its application to tensor PCA

by   Giulio Biroli, et al.
Cole Normale Suprieure
King's College London
Sapienza University of Rome

In many high-dimensional estimation problems the main task consists in minimizing a cost function, which is often strongly non-convex when scanned in the space of parameters to be estimated. A standard solution to flatten the corresponding rough landscape consists in summing the losses associated to different data points and obtain a smoother empirical risk. Here we propose a complementary method that works for a single data point. The main idea is that a large amount of the roughness is uncorrelated in different parts of the landscape. One can then substantially reduce the noise by evaluating an empirical average of the gradient obtained as a sum over many random independent positions in the space of parameters to be optimized. We present an algorithm, called Replicated Gradient Descent, based on this idea and we apply it to tensor PCA, which is a very hard estimation problem. We show that Replicated Gradient Descent over-performs physical algorithms such as gradient descent and approximate message passing and matches the best algorithmic thresholds known so far, obtained by tensor unfolding and methods based on sum-of-squares.


page 1

page 2

page 3

page 4


The Power of Normalization: Faster Evasion of Saddle Points

A commonly used heuristic in non-convex optimization is Normalized Gradi...

Marvels and Pitfalls of the Langevin Algorithm in Noisy High-dimensional Inference

Gradient-descent-based algorithms and their stochastic versions have wid...

Homotopy Analysis for Tensor PCA

Developing efficient and guaranteed nonconvex algorithms has been an imp...

Message Passing Descent for Efficient Machine Learning

We propose a new iterative optimization method for the Data-Fitting (DF)...

Please sign up or login with your details

Forgot password? Click here to reset