learning algorithms
Algorithms designed to automate the learning process in AI systems, enabling them to adapt and improve their performance based on input data and experiences rather than being explicitly programmed.
- A Sustainable AI Economy Needs Data Deals That Work for Generators
- Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games
- Error Forcing in Recurrent Neural Networks
- Formal Models of Active Learning from Contrastive Examples
- Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria
- Learning Juntas under Markov Random Fields
- Learning from positive and unlabeled examples -Finite size sample bounds
- Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning
- Price of Parsimony: Complexity of Fourier Sparsity Testing
- Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
- Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
- Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
- Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
- UEPI: Universal Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative Differential Equations
- metaTextGrad: Automatically optimizing language model optimizers