Publication

A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions

Chat with Graph Search

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Asymptotically Optimal Hardness for 𝑘-Set Packing and 𝑘-Matroid Intersection

Asynchronous Speedup in Decentralized Optimization

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Perturbed Utility Stochastic Traffic Assignment

Deep Learning Theory Through the Lens of Diagonal Linear Networks

BENIGN LANDSCAPES OF LOW-DIMENSIONAL RELAXATIONS FOR ORTHOGONAL SYNCHRONIZATION ON GENERAL GRAPHS

The Power of Two Matrices in Spectral Algorithms for Community Recovery

Scalable constrained optimization

Mesh-based topology, shape and sizing optimization of ribbed plates

The effect of smooth parametrizations on nonconvex optimization landscapes

Understanding generalization and robustness in modern deep learning

A Combination Technique for Optimal Control Problems Constrained by Random PDEs

Learning Barrier-Certified Polynomial Dynamical Systems for Obstacle Avoidance with Robots

On the Generalization of Stochastic Gradient Descent with Momentum

WILD SOLUTIONS TO SCALAR EULER-LAGRANGE EQUATIONS

The complexity of quantum support vector machines

A Reduced Order Model for Domain Decompositions with Non-conforming Interfaces

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Efficient Continual Finite-Sum Minimization