Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning
cs.LG, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/ahmednebli/Phase-HDC
Sources
- Symbolic Discovery of Optimization Algorithms
- THDC: Training Hyperdimensional Computing Models with Backpropagation
- 8-bit Optimizers via Block-wise Quantization
- TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
- Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
- Adam: A Method for Stochastic Optimization
- Unifying Sign and Magnitude for Optimizing Deep Vision Networks via ThermoLion
- Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function
- qFHRR: Rethinking Fourier Holographic Reduced Representations through Quantized Phase and Integer Arithmetic
- Training and Inference with Integers in Deep Neural Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks