Across the Loss Landscape with Progressive Growth
cs.LG, cs.AI
Submitted: 2026-08-25
Updated: 2026-08-25
Terminology
Sources
- Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
- Net2Net: Accelerating Learning via Knowledge Transfer
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Fantastic Generalization Measures are Nowhere to be Found
- Qualitatively characterizing neural network optimization problems
- Fantastic Generalization Measures and Where to Find Them
- Adam: A Method for Stochastic Optimization
- DARTS: Differentiable Architecture Search
- Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond
- Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally
- Why are Adaptive Methods Good for Attention Models?
- Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
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