← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Understanding Visual Feature Reliance through the Lens of Complexity NIPS 2024
Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery AAAI 2024
Testing Semantic Importance via Betting NIPS 2024
Simplicity Bias in Overparameterized Machine Learning AAAI 2024
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization NIPS 2024
Worst-Case Offline Reinforcement Learning with Arbitrary Data Support NIPS 2024
Local to Global: Learning Dynamics and Effect of Initialization for Transformers NIPS 2024
Can Transformers Learn n-gram Language Models? EMNLP 2024
Sample-efficient Bayesian Optimisation Using Known Invariances NIPS 2024
The Sample Complexity of Gradient Descent in Stochastic Convex Optimization NIPS 2024
Debiasing Evaluations That Are Biased by Evaluations JMLR 2024
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion NIPS 2024
PAC-Bayes Generalisation Bounds for Dynamical Systems including Stable RNNs AAAI 2024
The Limits of Differential Privacy in Online Learning NIPS 2024
A two-scale Complexity Measure for Deep Learning Models NIPS 2024
Which Is More Effective in Label Noise Cleaning, Correction or Filtering? AAAI 2024
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning NIPS 2024
High-Dimensional Analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm AAAI 2024
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning NIPS 2024
PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping AAAI 2024
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers NIPS 2024
FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in LLMs EMNLP 2024
Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise NIPS 2024
Fast Rates for Bandit PAC Multiclass Classification NIPS 2024
Achievable distributional robustness when the robust risk is only partially identified NIPS 2024