Model-based domain generalization
Despite remarkable success in a variety of applications, it is well-known that deep learning
can fail catastrophically when presented with out-of-distribution data. Toward addressing …
can fail catastrophically when presented with out-of-distribution data. Toward addressing …
Constrained-CNN losses for weakly supervised segmentation
Weakly-supervised learning based on, eg, partially labelled images or image-tags, is
currently attracting significant attention in CNN segmentation as it can mitigate the need for …
currently attracting significant attention in CNN segmentation as it can mitigate the need for …
Adversarial robustness with semi-infinite constrained learning
Despite strong performance in numerous applications, the fragility of deep learning to input
perturbations has raised serious questions about its use in safety-critical domains. While …
perturbations has raised serious questions about its use in safety-critical domains. While …
Sequential quadratic optimization for nonlinear equality constrained stochastic optimization
Sequential quadratic optimization algorithms are proposed for solving smooth nonlinear
optimization problems with equality constraints. The main focus is an algorithm proposed for …
optimization problems with equality constraints. The main focus is an algorithm proposed for …
Constrained deep networks: Lagrangian optimization via log-barrier extensions
This study investigates imposing hard inequality constraints on the outputs of convolutional
neural networks (CNN) during training. Several recent works showed that the theoretical and …
neural networks (CNN) during training. Several recent works showed that the theoretical and …
Deep differentiable grasp planner for high-dof grippers
We present an end-to-end algorithm for training deep neural networks to grasp novel
objects. Our algorithm builds all the essential components of a grasping system using a …
objects. Our algorithm builds all the essential components of a grasping system using a …
A stochastic sequential quadratic optimization algorithm for nonlinear-equality-constrained optimization with rank-deficient Jacobians
A sequential quadratic optimization algorithm is proposed for solving smooth nonlinear-
equality-constrained optimization problems in which the objective function is defined by an …
equality-constrained optimization problems in which the objective function is defined by an …
An adaptive stochastic sequential quadratic programming with differentiable exact augmented lagrangians
We consider solving nonlinear optimization problems with a stochastic objective and
deterministic equality constraints. We assume for the objective that its evaluation, gradient …
deterministic equality constraints. We assume for the objective that its evaluation, gradient …
Advancing non-convex and constrained learning: Challenges and opportunities
T Yang - AI Matters, 2019 - dl.acm.org
As data gets more complex and applications of machine learning (ML) algorithms for
decision-making broaden and diversify, traditional ML methods by minimizing an …
decision-making broaden and diversify, traditional ML methods by minimizing an …
Inexact sequential quadratic optimization for minimizing a stochastic objective function subject to deterministic nonlinear equality constraints
An algorithm is proposed, analyzed, and tested experimentally for solving stochastic
optimization problems in which the decision variables are constrained to satisfy equations …
optimization problems in which the decision variables are constrained to satisfy equations …