Model Compression with Exact Budget Constraints via Riemannian Manifolds

arXiv:2605.00649 · cs.LG · Submitted 2026-05-01 · Read on arXiv

cs.LG

Submitted: 2026-05-01

Updated: 2026-09-27

Code: https://github.com/IST-DASLab/RCO

Terminology

• Benchmark — 33× in this paper · explained in 2 episodes
• Quantization — 33× in this paper · explained in 12 episodes
• Adam — 32× in this paper · explained in 2 episodes
• Calibration — 32× in this paper · explained in 7 episodes
• Pruning — 30× in this paper · explained in 4 episodes
• Sparsity — 30× in this paper · explained in 4 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Perplexity — 10× in this paper · explained in 3 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Axioms — 7× in this paper · explained in 2 episodes
• Riemannian Constrained Optimization — 6× in this paper
• Trace — 6× in this paper · explained in 2 episodes
• Antithetic sampling — 4× in this paper · explained in 1 episode
• Robustness — 3× in this paper · explained in 5 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Elias — 2× in this paper · explained in 2 episodes
• Riemannian optimization — 2× in this paper · explained in 2 episodes
• Sample Efficiency — 2× in this paper · explained in 4 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
• RC-DARTS: Resource Constrained Differentiable Architecture Search
• REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
• EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
• CoopQ: Cooperative Game Inspired Layerwise Mixed Precision Quantization for LLMs

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