Listwise explanations for ranking models using multiple explainers
This paper proposes a novel approach towards better interpretability of a trained text-based
ranking model in a post-hoc manner. A popular approach for post-hoc interpretability text …
ranking model in a post-hoc manner. A popular approach for post-hoc interpretability text …
[PDF][PDF] Machine learning, linear algebra, and more: Is SQL all you need?
ABSTRACT SQL is the standard language for retrieving and manipulating relational data.
Although SQL is ubiquitous for simple analytical queries, it is rarely used for more complex …
Although SQL is ubiquitous for simple analytical queries, it is rarely used for more complex …
A simple and efficient tensor calculus
S Laue, M Mitterreiter, J Giesen - … of the AAAI Conference on Artificial …, 2020 - ojs.aaai.org
Computing derivatives of tensor expressions, also known as tensor calculus, is a
fundamental task in machine learning. A key concern is the efficiency of evaluating the …
fundamental task in machine learning. A key concern is the efficiency of evaluating the …
[PDF][PDF] NCVX: A general-purpose optimization solver for constrained machine and deep learning
Buyun Liang Plan B MS final defense Page 1 NCVX: A General-Purpose Optimization
Solver for Constrained Machine and Deep Learning Buyun Liang Apr 7, 2023 Page 2 …
Solver for Constrained Machine and Deep Learning Buyun Liang Apr 7, 2023 Page 2 …
Optimization and optimizers for adversarial robustness
Empirical robustness evaluation (RE) of deep learning models against adversarial
perturbations entails solving nontrivial constrained optimization problems. Existing …
perturbations entails solving nontrivial constrained optimization problems. Existing …
Optimization for classical machine learning problems on the gpu
Constrained optimization problems arise frequently in classical machine learning. There
exist frameworks addressing constrained optimization, for instance, CVXPY and GENO …
exist frameworks addressing constrained optimization, for instance, CVXPY and GENO …
Ncvx: A user-friendly and scalable package for nonconvex optimization in machine learning
Optimizing nonconvex (NCVX) problems, especially nonsmooth and constrained ones, is an
essential part of machine learning. However, it can be hard to reliably solve such problems …
essential part of machine learning. However, it can be hard to reliably solve such problems …
Addressing Machine Learning Problems in the Non-Negative Orthant
I Tsingalis, C Kotropoulos - IEEE Transactions on Emerging …, 2024 - ieeexplore.ieee.org
Frequently, equality constraints are imposed on the objective function of machine learning
algorithms aiming at increasing their robustness and generalization. In addition, non …
algorithms aiming at increasing their robustness and generalization. In addition, non …
Optimization for Robustness Evaluation beyond Metrics
Empirical evaluation of deep learning models against adversarial attacks entails solving
nontrivial constrained optimization problems. Popular algorithms for solving these …
nontrivial constrained optimization problems. Popular algorithms for solving these …
Optimization for Robustness Evaluation Beyond ℓp Metrics
Empirical evaluation of the adversarial robustness of deep learning models involves solving
non-trivial constrained optimization problems. Popular numerical algorithms to solve these …
non-trivial constrained optimization problems. Popular numerical algorithms to solve these …