A Discrepancy-Based Perspective on Dataset Condensation
cs.LG
Submitted: 2025-09-12
Updated: 2026-09-23
Terminology
Sources
- Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models
- Model compression as constrained optimization, with application to neural nets. Part I: general framework
- Model compression as constrained optimization, with application to neural nets. Part II: quantization
- A Closer Look at Few-shot Classification
- Deep Learning Scaling is Predictable, Empirically
- Distilling the Knowledge in a Neural Network
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- Scaling Laws for Neural Language Models
- Auto-Encoding Variational Bayes
- Dataset Distillation via the Wasserstein Metric
- DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching
- Conditional Generative Adversarial Nets
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- Unlocking Dataset Distillation with Diffusion Models
- Carbon Emissions and Large Neural Network Training
- Can we achieve robustness from data alone?
- Dataset Distillation
- Towards Robust Dataset Learning
- Understanding deep learning requires rethinking generalization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks