Search Results for author: Aaron Ferber

Found 11 papers, 1 papers with code

AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification

1 code implementation28 Oct 2024 Brendan Hogan, Anmol Kabra, Felipe Siqueira Pacheco, Laura Greenstreet, Joshua Fan, Aaron Ferber, Marta Ummus, Alecsander Brito, Olivia Graham, Lillian Aoki, Drew Harvell, Alex Flecker, Carla Gomes

Trust and interpretability are crucial for the use of Artificial Intelligence (AI) in scientific research, but current models often operate as black boxes offering limited transparency and justifications for their outputs.

Image Classification scientific discovery

Critic Loss for Image Classification

no code implementations23 Sep 2024 Brendan Hogan Rappazzo, Aaron Ferber, Carla Gomes

CrtCl formulates image classification training in a generator-critic framework, with a base classifier acting as a generator, and a correctness critic imposing a loss on the classifier.

Active Learning Classification +1

GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation

no code implementations23 Sep 2024 Brendan Hogan Rappazzo, Yingheng Wang, Aaron Ferber, Carla Gomes

The ability to form, retrieve, and reason about memories in response to stimuli serves as the cornerstone for general intelligence - shaping entities capable of learning, adaptation, and intuitive insight.

Question Answering RAG +1

Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints

no code implementations28 Feb 2024 Lingkai Kong, Yuanqi Du, Wenhao Mu, Kirill Neklyudov, Valentin De Bortoli, Dongxia Wu, Haorui Wang, Aaron Ferber, Yi-An Ma, Carla P. Gomes, Chao Zhang

To constrain the optimization process to the data manifold, we reformulate the original optimization problem as a sampling problem from the product of the Boltzmann distribution defined by the objective function and the data distribution learned by the diffusion model.

Learning Lagrangian Multipliers for the Travelling Salesman Problem

no code implementations22 Dec 2023 Augustin Parjadis, Quentin Cappart, Bistra Dilkina, Aaron Ferber, Louis-Martin Rousseau

Lagrangian relaxation is a versatile mathematical technique employed to relax constraints in an optimization problem, enabling the generation of dual bounds to prove the optimality of feasible solutions and the design of efficient propagators in constraint programming (such as the weighted circuit constraint).

GenCO: Generating Diverse Designs with Combinatorial Constraints

no code implementations3 Oct 2023 Aaron Ferber, Arman Zharmagambetov, Taoan Huang, Bistra Dilkina, Yuandong Tian

Deep generative models like GAN and VAE have shown impressive results in generating unconstrained objects like images.

Combinatorial Optimization Image Generation

SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems

no code implementations22 Oct 2022 Aaron Ferber, Taoan Huang, Daochen Zha, Martin Schubert, Benoit Steiner, Bistra Dilkina, Yuandong Tian

Optimization problems with nonlinear cost functions and combinatorial constraints appear in many real-world applications but remain challenging to solve efficiently compared to their linear counterparts.

Combinatorial Optimization

Learning Pseudo-Backdoors for Mixed Integer Programs

no code implementations9 Jun 2021 Aaron Ferber, Jialin Song, Bistra Dilkina, Yisong Yue

In addition, we compare our learned approach against Gurobi, a state-of-the-art MIP solver, demonstrating that our method can be used to improve solver performance.

Combinatorial Optimization

MIPaaL: Mixed Integer Program as a Layer

no code implementations12 Jul 2019 Aaron Ferber, Bryan Wilder, Bistra Dilkina, Milind Tambe

It has been successfully applied to several limited combinatorial problem classes, such as those that can be expressed as linear programs (LP), and submodular optimization.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.