181 citations · 620 across the 171 of their papers we have counts for
16 papers · 1 filter
How I Learned to Stop Worrying and Love Retraining
Max Zimmer, Christoph Spiegel, Sebastian Pokutta
Many Neural Network Pruning approaches consist of several iterative training and pruning steps, seemingly losing a significant amount of their performance after pruning and then re…
Sparser Kernel Herding with Pairwise Conditional Gradients without Swap Steps
Kazuma Tsuji, Ken'ichiro Tanaka, Sebastian Pokutta
The Pairwise Conditional Gradients (PCG) algorithm is a powerful extension of the Frank-Wolfe algorithm leading to particularly sparse solutions, which makes PCG very appealing for…
Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
Jan Macdonald, Mathieu Besançon, Sebastian Pokutta
We study the effects of constrained optimization formulations and Frank-Wolfe algorithms for obtaining interpretable neural network predictions. Reformulating the Rate-Distortion E…
Fast Algorithms for Packing Proportional Fairness and its Dual
Francisco Criado, David Martínez-Rubio, Sebastian Pokutta
The proportional fair resource allocation problem is a major problem studied in flow control of networks, operations research, and economic theory, where it has found numerous appl…
Efficient Online-Bandit Strategies for Minimax Learning Problems
Christophe Roux, Elias Wirth, Sebastian Pokutta +1
Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or learning with non-standard aggregated losses. More specifically, these…
An Algorithm-Independent Measure of Progress for Linear Constraint Propagation
Boro Sofranac, Ambros Gleixner, Sebastian Pokutta
Propagation of linear constraints has become a crucial sub-routine in modern Mixed-Integer Programming (MIP) solvers. In practice, iterative algorithms with tolerance-based stoppin…
Scalable Frank-Wolfe on Generalized Self-concordant Functions via Simple Steps
Alejandro Carderera, Mathieu Besançon, Sebastian Pokutta
Generalized self-concordance is a key property present in the objective function of many important learning problems. We establish the convergence rate of a simple Frank-Wolfe vari…
FrankWolfe.jl: a high-performance and flexible toolbox for Frank-Wolfe algorithms and Conditional Gradients
Mathieu Besançon, Alejandro Carderera, Sebastian Pokutta
We present FrankWolfe.jl, an open-source implementation of several popular Frank-Wolfe and Conditional Gradients variants for first-order constrained optimization. The package is d…
Learning to Schedule Heuristics in Branch-and-Bound
Antonia Chmiela, Elias B. Khalil, Ambros Gleixner +2
Primal heuristics play a crucial role in exact solvers for Mixed Integer Programming (MIP). While solvers are guaranteed to find optimal solutions given sufficient time, real-world…
Linear Bandits on Uniformly Convex Sets
Thomas Kerdreux, Christophe Roux, Alexandre d'Aspremont +1
Linear bandit algorithms yield pseudo-regret bounds on compact convex action sets and two types of structural assu…
Local and Global Uniform Convexity Conditions
Thomas Kerdreux, Alexandre d'Aspremont, Sebastian Pokutta
We review various characterizations of uniform convexity and smoothness on norm balls in finite-dimensional spaces and connect results stemming from the geometry of Banach spaces w…
Dual Prices for Frank--Wolfe Algorithms
Gábor Braun, Sebastian Pokutta
In this note we observe that for constrained convex minimization problems over a polytope , dual prices for the linear program $\min_{z \in P} \nabla f(x) z…
Parameter-free Locally Accelerated Conditional Gradients
Alejandro Carderera, Jelena Diakonikolas, Cheuk Yin Lin +1
Projection-free conditional gradient (CG) methods are the algorithms of choice for constrained optimization setups in which projections are often computationally prohibitive but li…
Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial training
Sebastian Pokutta, Huan Xu
We revisit the concept of "adversary" in online learning, motivated by solving robust optimization and adversarial training using online learning methods. While one of the classica…
Complexity of Linear Minimization and Projection on Some Sets
Cyrille W. Combettes, Sebastian Pokutta
The Frank-Wolfe algorithm is a method for constrained optimization that relies on linear minimizations, as opposed to projections. Therefore, a motivation put forward in a large bo…
CINDy: Conditional gradient-based Identification of Non-linear Dynamics -- Noise-robust recovery
Alejandro Carderera, Sebastian Pokutta, Christof Schütte +1
Governing equations are essential to the study of nonlinear dynamics, often enabling the prediction of previously unseen behaviors as well as the inclusion into control strategies.…