AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
cs.LG, cs.AI
Submitted: 2025-05-18
Updated: 2026-09-23
Terminology
Sources
- Critical Learning Periods in Deep Neural Networks
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Improved Baselines with Momentum Contrastive Learning
- CINIC-10 is not ImageNet or CIFAR-10
- Learning Robust Representations via Multi-View Information Bottleneck
- On the duality between contrastive and non-contrastive self-supervised learning
- Understanding Dimensional Collapse in Contrastive Self-supervised Learning
- HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms
- Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss
- Representation Learning with Contrastive Predictive Coding
- Projection Head is Secretly an Information Bottleneck
- Information Flow in Self-Supervised Learning
- LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
- The information bottleneck method
- Matrix Information Theory for Self-Supervised Learning
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