IOL Lab (ZIB-IOL)

IOL Lab

ZIB-IOL

Geek Repo

Working on optimization and learning at the intersection of mathematics and computer science

Location:Germany

Home Page:https://iol.zib.de

Github PK Tool:Github PK Tool

IOL Lab's repositories

FrankWolfe.jl

Julia implementation for various Frank-Wolfe and Conditional Gradient variants

Language:JuliaLicense:MITStargazers:92Issues:5Issues:117

Boscia.jl

Mixed-Integer Convex Programming: Branch-and-bound with Frank-Wolfe-based convex relaxations

Language:JuliaLicense:MITStargazers:22Issues:2Issues:60

StochasticFrankWolfe

Implementation of the Stochastic Frank Wolfe algorithm in TensorFlow and Pytorch.

CINDy

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

Language:PythonLicense:MITStargazers:8Issues:2Issues:0

SMS

Code to reproduce the experiments of the ICLR24-paper: "Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging"

Language:PythonStargazers:7Issues:1Issues:0

BIMP

Code to reproduce the experiments of ICLR2023-paper: How I Learned to Stop Worrying and Love Retraining

Language:PythonStargazers:6Issues:1Issues:0

FrankWolfe-book-code

Python implementation of Frank-Wolfe and Conditional Gradient algorithms

Language:PythonLicense:MITStargazers:4Issues:2Issues:0

fw-rde

Official implementation of the paper "Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings" by J. Macdonald, M. Besançon, and S. Pokutta (2021).

Language:PythonLicense:MITStargazers:4Issues:2Issues:2

BellPolytopes.jl

This julia package addresses the membership problem for local polytopes: it constructs Bell inequalities and local models in multipartite Bell scenarios with binary outcomes.

Language:JuliaLicense:MITStargazers:3Issues:1Issues:3

CGAVI

Code for the paper: Wirth, E.S. and Pokutta, S., 2022, May. Conditional gradients for the approximately vanishing ideal. In International Conference on Artificial Intelligence and Statistics (pp. 2191-2209). PMLR.

Language:PythonLicense:MITStargazers:3Issues:1Issues:0

ApproximateVanishingIdeals.jl

approximate vanishing ideal computations

Language:JuliaLicense:MITStargazers:2Issues:0Issues:5
Language:PythonLicense:Apache-2.0Stargazers:2Issues:1Issues:3

open_loop_fw

Code for the paper: Wirth, E., Pokutta, S., and Kerdreux, T. (2023). Acceleration of Frank-Wolfe Algorithms with Open-Loop Step-Sizes. To Appear in Proceedings of AISTATS.

Language:PythonLicense:MITStargazers:2Issues:1Issues:0

AAPPR.jl

Accelerated and Sparse Algorithms for Approximate Personalized PageRank and Beyond

Language:JuliaLicense:MITStargazers:1Issues:2Issues:0

compression-aware-SFW

Code to reproduce the experiments of "Compression-aware Training of Neural Networks using Frank-Wolfe"

Language:PythonStargazers:1Issues:1Issues:0

KernelHerding.jl

A package demonstrating Kernel Herding with Frank-Wolfe algorithms

Language:JuliaLicense:MITStargazers:1Issues:1Issues:0

merlin-arthur-classifiers

Implementation of Merlin-Arthur-Classifier Framework presented at AISTATS24.

Language:PythonStargazers:1Issues:2Issues:0
Stargazers:0Issues:1Issues:0

AffineInvariantOLFW

Code for the paper Accelerated Affine-Invariant Vonvergence Rates of the Frank-Wolfe Algorithm with Open-Loop Step-Sizes

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

avi_at_scale

Code for the paper: [Wirth, E., Kera, H., and Pokutta, S. (2022). Approximate vanishing ideal computations at scale.](https://arxiv.org/abs/2207.01236)

Language:PythonLicense:MITStargazers:0Issues:2Issues:0

fw-generalized-selfconcordant

Repository for the NeurIPS2021 paper "Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions"

Language:JuliaLicense:MITStargazers:0Issues:1Issues:0
Language:JuliaStargazers:0Issues:0Issues:0

OptimalDesignWithBoscia

Solving the Exact Optimal Experiment Design Problem using the convex mixed-integer solver Boscia.jl

Language:JuliaStargazers:0Issues:1Issues:0
Language:JuliaStargazers:0Issues:1Issues:0

CombinatorialLinearOracles.jl

Linear Minimization Oracles for Combinatorial Problems

Language:JuliaLicense:MITStargazers:0Issues:1Issues:0

gpu-domain-propagator

Sequantial C++ (CPU), and a CUDA (GPU) implementation of Domain Propagation for Mixed-Integer Programming problems

Language:CudaStargazers:0Issues:1Issues:0