Flawed in Nature, Perfect through Evolution
cs.LG, cs.AI, cs.NE
Submitted: 2026-08-31
Updated: 2026-08-31
Comments: 32 pages, 16 figures; appeared in ADI (September 2026)
Journal ref: ADI 3, 1-32 (2026)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Lower Bounds for Locally Private Estimation via Communication Complexity
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
- Gradient Descent Happens in a Tiny Subspace
- LoRA: Low-Rank Adaptation of Large Language Models
- Population Based Training of Neural Networks
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- Measuring the Intrinsic Dimension of Objective Landscapes
- BitTensor: A Peer-to-Peer Intelligence Market
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Attention Is All You Need
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
- Continual Learning Through Synaptic Intelligence
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