Learning Theory

Optimization Can Learn Johnson Lindenstrauss Embeddings NeurIPS 2024 Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition NeurIPS 2024 Oracle-Efficient Hybrid Online Learning with Unknown Distribution COLT 2024 Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization ICLR 2024 Out-of-Domain Generalization in Dynamical Systems Reconstruction ICML 2024 Out-of-Variable Generalisation for Discriminative Models ICLR 2024 Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms NeurIPS 2024 Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality NeurIPS 2024 Overparametrized Multi-layer Neural Networks: Uniform Concentration of Neural Tangent Kernel and Convergence of Stochastic Gradient Descent JMLR 2024 PAC-Bayes-Chernoff bounds for unbounded losses NeurIPS 2024 PAC-Bayes Generalisation Bounds for Dynamical Systems including Stable RNNs AAAI 2024 PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models ICML 2024 PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning ICML 2024 PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect ICML 2024 Parameterized Complexity of Kidney Exchange Revisited IJCAI 2024 Performance Bounds for Active Binary Testing with Information Maximization ICML 2024 Performative Prediction with Bandit Feedback: Learning through Reparameterization ICML 2024 Pi-DUAL: Using privileged information to distinguish clean from noisy labels ICML 2024 Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners ICML 2024 Plug-in Performative Optimization ICML 2024 Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis AISTATS 2024 Position: Do pretrained Transformers Learn In-Context by Gradient Descent? ICML 2024 Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training ICML 2024 Position: Future Directions in the Theory of Graph Machine Learning ICML 2024 Position: Understanding LLMs Requires More Than Statistical Generalization ICML 2024