Search Results for author:
Found 4 papers, 1 papers with code
Near-Optimal Solutions of Constrained Learning Problems
These requirements can be imposed (with generalization guarantees) by formulating constrained learning problems that can then be tackled by dual ascent algorithms.
Primal-Dual Continual Learning: Stability and Plasticity through Lagrange Multipliers
Continual learning is inherently a constrained learning problem.
Neural Networks with Quantization Constraints
Furthermore, we show that dual variables indicate the sensitivity of the objective with respect to constraint perturbations.
A Lagrangian Duality Approach to Active Learning
We consider the pool-based active learning problem, where only a subset of the training data is labeled, and the goal is to query a batch of unlabeled samples to be labeled so as to maximally improve model performance.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
