To Convexify or Not? Regression with Clustering Penalties on Graphs

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.

Residual stresses in hot-rolled wide flange steel cross sections may lead to premature yielding, accelerated corrosion and brittle fracture of steel members. The above phenomena lead to a loss of a steel member's stiffness and resistance under mechanical l ...

One of the main goal of Artificial Intelligence is to develop models capable of providing valuable predictions in real-world environments. In particular, Machine Learning (ML) seeks to design such models by learning from examples coming from this same envi ...

Submodular functions are a widely studied topic in theoretical computer science. They have found several applications both theoretical and practical in the fields of economics, combinatorial optimization and machine learning. More recently, there have also ...

We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate first-order critical ...

This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the problem and then o ...

We consider the problem of provably finding a stationary point of a smooth function to be minimized on the variety of bounded-rank matrices. This turns out to be unexpectedly delicate. We trace the difficulty back to a geometric obstacle: On a nonsmooth se ...

We propose an adaptive variance-reduction method, called AdaSpider, for minimization of L-smooth, non-convex functions with a finite-sum structure. In essence, AdaSpider combines an AdaGrad-inspired [Duchi et al., 2011, McMahan & Streeter, 2010], but a fai ...

In this thesis, we reveal that supervised learning and inverse problems share similar mathematical foundations. Consequently, we are able to present a unified variational view of these tasks that we formulate as optimization problems posed over infinite-di ...

In this paper, we analyze the recently proposed stochastic primal-dual hybrid gradient (SPDHG) algorithm and provide new theoretical results. In particular, we prove almost sure convergence of the iterates to a solution with convexity and linear convergenc ...

This paper focuses on the distributionally robust dispatch for integrated transmission-distribution (ITD) systems via distributed optimization. Existing distributed algorithms usually require synchronization of all subproblems, which could be hard to scale ...

State-of-the-art microstructure imaging methods usually fit biophysical models to the diffusion MRI data on a voxel-by-voxel basis using non-linear procedures that require both long acquisitions and processing time. We recently introduced AMICO, a framewor ...

To Convexify or Not? Regression with Clustering Penalties on Graphs

Chat with Graph Search

Proposed residual stress model for hot‐rolled wide flange steel cross sections

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Streaming and Matching Problems with Submodular Functions

An Accelerated First-Order Method for Non-convex Optimization on Manifolds

Proximal Point Imitation Learning

Finding stationary points on bounded-rank matrices: a geometric hurdle and a smooth remedy

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Optimization Over Banach Spaces: A Unified View on Supervised Learning and Inverse Problems

On The Convergence Of Stochastic Primal-Dual Hybrid Gradient

Distributionally Robust Joint Chance-Constrained Dispatch for Integrated Transmission-Distribution Systems via Distributed Optimization

Reducing acquisition time for axon diameter mapping using global optimization in the spatial-angular-microstructure space