Group-Sparse Model Selection: Hardness and Relaxations

Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. The main promise of these models is the recovery of ``interpretable" signals along with the identification of their constituent groups. To this end, we establish a combinatorial framework for group-model selection problems and highlight the underlying tractability issues revolving around such notions of interpretability when the regression matrix is simply the identity operator. We show that, in general, claims of correctly identifying the groups with convex relaxations would lead to polynomial time solution algorithms for a well-known NP-hard problem, called the weighted maximum cover problem. Instead, leveraging a graph-based understanding of group models, we describe group structures which enable correct model identification in polynomial time via dynamic programming. We also show that group structures that lead to totally unimodular constraints have tractable discrete as well as convex relaxations. Finally, we study the Pareto frontier of budgeted group-sparse approximations for the tree-based sparsity model and illustrate identification and computation trade-offs between our framework and the existing convex relaxations.

Tractability of interpretability via selection of group-sparse models

Luca Baldassarre, Nirav Bhan, Volkan Cevher

Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. A promise of these models is to lead to “interpretable” signals for which we identify its constituent groups, however we show that, in general, claims of correctly identifying the groups with convex relaxations would lead to polynomial time solution algorithms for an NP-hard problem. Instead, leveraging a graph-based understanding of group models, we describe group structures which enable correct model identification in polynomial time via dynamic programming. We also show that group structures that lead to totally unimodular constraints have tractable relaxations. Finally, we highlight the non-convexity of the Pareto frontier of group-sparse approximations and what it means for tractability.

2013

Strengths and Limitations of Linear Programming Relaxations

Abbas Bazzi

Many of the currently best-known approximation algorithms for NP-hard optimization problems are based on Linear Programming (LP) and Semi-definite Programming (SDP) relaxations. Given its power, this class of algorithms seems to contain the most favourable candidates for outperforming the current state-of-the-art approximation guarantees for NP-hard problems, for which there still exists a gap between the inapproximability results and the approximation guarantees that we know how to achieve in polynomial time. In this thesis, we address both the power and the limitations of these relaxations, as well as the connection between the shortcomings of these relaxations and the inapproximability of the underlying problem. In the first part, we study the limitations of LP relaxations of well-known graph problems such as the Vertex Cover problem and the Independent Set problem. We prove that any small LP relaxation for the aforementioned problems, cannot have an integrality gap strictly better than

2

and

\omega(1)

, respectively. Furthermore, our lower bound for the Independent Set problem also holds for any SDP relaxation. Prior to our work, it was only known that such LP relaxations cannot have an integrality gap better than

1.5

for the Vertex Cover Problem, and better than

2

for the Independent Set problem. In the second part, we study the so-called knapsack cover inequalities that are used in the current best relaxations for numerous combinatorial optimization problems of covering type. In spite of their widespread use, these inequalities yield LP relaxations of exponential size, over which it is not known how to optimize exactly in polynomial time. We address this issue and obtain LP relaxations of quasi-polynomial size that are at least as strong as that given by the knapsack cover inequalities. In the last part, we show a close connection between structural hardness for k-partite graphs and tight inapproximability results for scheduling problems with precedence constraints. This connection is inspired by a family of integrality gap instances of a certain LP relaxation. Assuming the hardness of an optimization problem on k-partite graphs, we obtain a hardness of

2-\varepsilon

for the problem of minimizing the makespan for scheduling with preemption on identical parallel machines, and a super constant inapproximability for the problem of scheduling on related parallel machines. Prior to this result, it was only known that the first problem does not admit a PTAS, and the second problem is NP-hard to approximate within a factor strictly better than 2, assuming the Unique Games Conjecture.

EPFL2017

Learning with Structured Sparsity: From Discrete to Convex and Back.

Marwa El Halabi

In modern-data analysis applications, the abundance of data makes extracting meaningful information from it challenging, in terms of computation, storage, and interpretability. In this setting, exploiting sparsity in data has been essential to the development of scalable methods to problems in machine learning, statistics and signal processing. However, in various applications, the input variables exhibit structure beyond simple sparsity. This motivated the introduction of structured sparsity models, which capture such sophisticated structures, leading to a significant performance gains and better interpretability. Structured sparse approaches have been successfully applied in a variety of domains including computer vision, text processing, medical imaging, and bioinformatics. The goal of this thesis is to improve on these methods and expand their success to a wider range of applications. We thus develop novel methods to incorporate general structure a priori in learning problems, which balance computational and statistical efficiency trade-offs. To achieve this, our results bring together tools from the rich areas of discrete and convex optimization. Applying structured sparsity approaches in general is challenging because structures encountered in practice are naturally combinatorial. An effective approach to circumvent this computational challenge is to employ continuous convex relaxations. We thus start by introducing a new class of structured sparsity models, able to capture a large range of structures, which admit tight convex relaxations amenable to efficient optimization. We then present an in-depth study of the geometric and statistical properties of convex relaxations of general combinatorial structures. In particular, we characterize which structure is lost by imposing convexity and which is preserved. We then focus on the optimization of the convex composite problems that result from the convex relaxations of structured sparsity models. We develop efficient algorithmic tools to solve these problems in a non-Euclidean setting, leading to faster convergence in some cases. Finally, to handle structures that do not admit meaningful convex relaxations, we propose to use, as a heuristic, a non-convex proximal gradient method, efficient for several classes of structured sparsity models. We further extend this method to address a probabilistic structured sparsity model, we introduce to model approximately sparse signals.

EPFL2018