
Efficient OnlineBandit Strategies for Minimax Learning Problems
Several learning problems involve solving minmax problems, e.g., empiri...
read it

Simple steps are all you need: FrankWolfe and generalized selfconcordant functions
Generalized selfconcordance is a key property present in the objective ...
read it

Learning to Schedule Heuristics in BranchandBound
Primal heuristics play a crucial role in exact solvers for Mixed Integer...
read it

Linear Bandits on Uniformly Convex Sets
Linear bandit algorithms yield 𝒪̃(n√(T)) pseudoregret bounds on compact...
read it

Parameterfree Locally Accelerated Conditional Gradients
Projectionfree conditional gradient (CG) methods are the algorithms of ...
read it

Local and Global Uniform Convexity Conditions
We review various characterizations of uniform convexity and smoothness ...
read it

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...
read it

Complexity of Linear Minimization and Projection on Some Sets
The FrankWolfe algorithm is a method for constrained optimization that ...
read it

CINDy: Conditional gradientbased Identification of Nonlinear Dynamics – Noiserobust recovery
Governing equations are essential to the study of nonlinear dynamics, of...
read it

Deep Neural Network Training with FrankWolfe
This paper studies the empirical efficacy and benefits of using projecti...
read it

ProjectionFree Adaptive Gradients for LargeScale Optimization
The complexity in largescale optimization can lie in both handling the ...
read it

Accelerating Domain Propagation: an Efficient GPUParallel Algorithm over Sparse Matrices
Fast domain propagation of linear constraints has become a crucial compo...
read it

Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization
Descent directions such as movement towards FrankWolfe vertices, away s...
read it

Boosting FrankWolfe by Chasing Gradients
The FrankWolfe algorithm has become a popular firstorder optimization ...
read it

Secondorder Conditional Gradients
Constrained secondorder convex optimization algorithms are the method o...
read it

IPBoost – NonConvex Boosting via Integer Programming
Recently nonconvex optimization approaches for solving machine learning...
read it

On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness
Submodular maximization has been widely studied over the past decades, m...
read it

Revisiting the Approximate Carathéodory Problem via the FrankWolfe Algorithm
The approximate Carathéodory theorem states that given a polytope P, eac...
read it

Locally Accelerated Conditional Gradients
Conditional gradient methods form a class of projectionfree firstorder...
read it

Blended Matching Pursuit
Matching pursuit algorithms are an important class of algorithms in sign...
read it

An OnlineLearning Approach to Inverse Optimization
In this paper, we demonstrate how to learn the objective function of a d...
read it

Principled Deep Neural Network Training through Linear Programming
Deep Learning has received significant attention due to its impressive p...
read it

Efficient algorithms for robust submodular maximization under matroid constraints
In this work, we consider robust submodular maximization with matroid co...
read it

Limits of Treewidthbased tractability in Optimization
Sparse structures are frequently sought when pursuing tractability in op...
read it

Blended Conditional Gradients: the unconditioning of conditional gradients
We present a blended conditional gradient approach for minimizing a smoo...
read it

Reinforcement Learning under Model Mismatch
We study reinforcement learning under model misspecification, where we d...
read it

Conditional Accelerated Lazy Stochastic Gradient Descent
In this work we introduce a conditional accelerated lazy stochastic grad...
read it

Sequential Information Guided Sensing
We study the value of information in sequential compressed sensing by ch...
read it

Sequential Sensing with Model Mismatch
We characterize the performance of sequential information guided sensing...
read it

InfoGreedy sequential adaptive compressed sensing
We present an informationtheoretic framework for sequential adaptive co...
read it
Sebastian Pokutta
is this you? claim profile