Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing
cs.LG, eess.IV, math.OC
Submitted: 2026-01-23
Updated: 2026-10-30
Comments: https://openreview.net/forum?id=Xi1UWSFooI
Journal ref: Transactions on Machine Learning Research, 2026
Code: https://github.com/dadoPuccio/ConstrainedLearning
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization
- Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
- Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning
- Adam: A Method for Stochastic Optimization
- Position: Adopt Constraints Over Fixed Penalties in Deep Learning
- Achieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach
- Training neural networks under physical constraints using a stochastic augmented Lagrangian approach
- Lagrangian dual framework for conservative neural network solutions of kinetic equations
- ASPEN: An Additional Sampling Penalty Method for Finite-Sum Optimization Problems with Nonlinear Equality Constraints
- Fast Convergence of Stochastic Gradient Descent under a Strong Growth Condition
- Densely Connected Convolutional Networks
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis