Sebastian Pokutta

research

∙ 06/29/2023

Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging

Neural networks can be significantly compressed by pruning, leading to s...

0 Max Zimmer, et al. ∙

research

∙ 05/25/2023

Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties

In this work, we study optimization problems of the form min_x max_y f(x...

0 David Martinez Rubio, et al. ∙

research

∙ 04/04/2023

Online Learning for Scheduling MIP Heuristics

Mixed Integer Programming (MIP) is NP-hard, and yet modern solvers often...

0 Antonia Chmiela, et al. ∙

research

∙ 11/26/2022

Accelerated Riemannian Optimization: Handling Constraints with a Prox to Bound Geometric Penalties

We propose a globally-accelerated, first-order method for the optimizati...

0 David Martinez Rubio, et al. ∙

research

∙ 08/23/2022

Convex integer optimization with Frank-Wolfe methods

Mixed-integer nonlinear optimization is a broad class of problems that f...

0 Deborah Hendrych, et al. ∙

research

∙ 07/04/2022

Approximate Vanishing Ideal Computations at Scale

The approximate vanishing ideal of a set of points X = {𝐱_1, …, 𝐱_m}⊆ [0...

0 Elias Wirth, et al. ∙

research

∙ 06/01/2022

Merlin-Arthur Classifiers: Formal Interpretability with Interactive Black Boxes

We present a new theoretical framework for making black box classifiers ...

0 Stephan Wäldchen, et al. ∙

research

∙ 05/24/2022

Compression-aware Training of Neural Networks using Frank-Wolfe

Many existing Neural Network pruning approaches either rely on retrainin...

0 Max Zimmer, et al. ∙

research

∙ 04/11/2022

Optimizing a low-dimensional convex function over a high-dimensional cube

For a matrix W ∈ℤ^m × n, m ≤ n, and a convex function g: ℝ^m →ℝ, we are ...

0 Christoph Hunkenschröder, et al. ∙

research

∙ 03/04/2022

The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights

Combinatorial optimization is a well-established area in operations rese...

12 Maxime Gasse, et al. ∙

research

∙ 02/23/2022

Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four

One of the goals of Explainable AI (XAI) is to determine which input com...

4 Stephan Wäldchen, et al. ∙

research

∙ 11/01/2021

Back to Basics: Efficient Network Compression via IMP

Network pruning is a widely used technique for effectively compressing D...

0 Max Zimmer, et al. ∙

research

∙ 10/15/2021

Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

We study the effects of constrained optimization formulations and Frank-...

0 Jan Macdonald, et al. ∙

research

∙ 05/28/2021

Efficient Online-Bandit Strategies for Minimax Learning Problems

Several learning problems involve solving min-max problems, e.g., empiri...

0 Christophe Roux, et al. ∙

research

∙ 05/28/2021

Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions

Generalized self-concordance is a key property present in the objective ...

10 Alejandro Carderera, et al. ∙

research

∙ 03/18/2021

Learning to Schedule Heuristics in Branch-and-Bound

Primal heuristics play a crucial role in exact solvers for Mixed Integer...

0 Antonia Chmiela, et al. ∙

research

∙ 03/10/2021

Linear Bandits on Uniformly Convex Sets

Linear bandit algorithms yield 𝒪̃(n√(T)) pseudo-regret bounds on compact...

0 Thomas Kerdreux, et al. ∙

research

∙ 02/12/2021

Parameter-free Locally Accelerated Conditional Gradients

Projection-free conditional gradient (CG) methods are the algorithms of ...

0 Alejandro Carderera, et al. ∙

research

∙ 02/09/2021

Local and Global Uniform Convexity Conditions

We review various characterizations of uniform convexity and smoothness ...

0 Thomas Kerdreux, et al. ∙

research

∙ 01/27/2021

Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial training

We revisit the concept of "adversary" in online learning, motivated by s...

0 Sebastian Pokutta, et al. ∙

research

∙ 01/25/2021

Complexity of Linear Minimization and Projection on Some Sets

The Frank-Wolfe algorithm is a method for constrained optimization that ...

0 Cyrille W. Combettes, et al. ∙

research

∙ 01/07/2021

CINDy: Conditional gradient-based Identification of Non-linear Dynamics – Noise-robust recovery

Governing equations are essential to the study of nonlinear dynamics, of...

0 Alejandro Carderera, et al. ∙

research

∙ 10/14/2020

Deep Neural Network Training with Frank-Wolfe

This paper studies the empirical efficacy and benefits of using projecti...

0 Sebastian Pokutta, et al. ∙

research

∙ 09/29/2020

Projection-Free Adaptive Gradients for Large-Scale Optimization

The complexity in large-scale optimization can lie in both handling the ...

0 Cyrille W. Combettes, et al. ∙

research

∙ 09/16/2020

Accelerating Domain Propagation: an Efficient GPU-Parallel Algorithm over Sparse Matrices

Fast domain propagation of linear constraints has become a crucial compo...

0 Boro Sofranac, et al. ∙

research

∙ 06/15/2020

Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization

Descent directions such as movement towards Frank-Wolfe vertices, away s...

0 Hassan Mortagy, et al. ∙

research

∙ 03/13/2020

Boosting Frank-Wolfe by Chasing Gradients

The Frank-Wolfe algorithm has become a popular first-order optimization ...

0 Cyrille W. Combettes, et al. ∙

research

∙ 02/20/2020

Second-order Conditional Gradients

Constrained second-order convex optimization algorithms are the method o...

0 Alejandro Carderera, et al. ∙

research

∙ 02/11/2020

IPBoost – Non-Convex Boosting via Integer Programming

Recently non-convex optimization approaches for solving machine learning...

0 Marc E. Pfetsch, et al. ∙

research

∙ 02/10/2020

On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness

Submodular maximization has been widely studied over the past decades, m...

0 Alfredo Torrico, et al. ∙

research

∙ 11/11/2019

Revisiting the Approximate Carathéodory Problem via the Frank-Wolfe Algorithm

The approximate Carathéodory theorem states that given a polytope P, eac...

0 Cyrille W. Combettes, et al. ∙

research

∙ 06/19/2019

Locally Accelerated Conditional Gradients

Conditional gradient methods form a class of projection-free first-order...

0 Alejandro Carderera, et al. ∙

research

∙ 04/28/2019

Blended Matching Pursuit

Matching pursuit algorithms are an important class of algorithms in sign...

0 Cyrille W. Combettes, et al. ∙

research

∙ 10/30/2018

An Online-Learning Approach to Inverse Optimization

In this paper, we demonstrate how to learn the objective function of a d...

0 Andreas Bärmann, et al. ∙

research

∙ 10/07/2018

Principled Deep Neural Network Training through Linear Programming

Deep Learning has received significant attention due to its impressive p...

0 Daniel Bienstock, et al. ∙

research

∙ 07/25/2018

Efficient algorithms for robust submodular maximization under matroid constraints

In this work, we consider robust submodular maximization with matroid co...

0 Sebastian Pokutta, et al. ∙

research

∙ 07/06/2018

Limits of Treewidth-based tractability in Optimization

Sparse structures are frequently sought when pursuing tractability in op...

0 Yuri Faenza, et al. ∙

research

∙ 05/18/2018

Blended Conditional Gradients: the unconditioning of conditional gradients

We present a blended conditional gradient approach for minimizing a smoo...

0 Gabor Braun, et al. ∙

research

∙ 06/15/2017

Reinforcement Learning under Model Mismatch

We study reinforcement learning under model misspecification, where we d...

0 Aurko Roy, et al. ∙

research

∙ 03/16/2017

Conditional Accelerated Lazy Stochastic Gradient Descent

In this work we introduce a conditional accelerated lazy stochastic grad...

0 Guanghui Lan, et al. ∙

research

∙ 09/01/2015

Sequential Information Guided Sensing

We study the value of information in sequential compressed sensing by ch...

0 Ruiyang Song, et al. ∙

research

∙ 01/26/2015

Sequential Sensing with Model Mismatch

We characterize the performance of sequential information guided sensing...

0 Ruiyang Song, et al. ∙

research

∙ 07/02/2014

Info-Greedy sequential adaptive compressed sensing

We present an information-theoretic framework for sequential adaptive co...

0 Gabor Braun, et al. ∙

Sebastian Pokutta

Featured Co-authors