← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs NIPS 2024
From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach NIPS 2024
Symmetries in Overparametrized Neural Networks: A Mean Field View NIPS 2024
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits NIPS 2024
Provable Partially Observable Reinforcement Learning with Privileged Information NIPS 2024
A Canonicalization Perspective on Invariant and Equivariant Learning NIPS 2024
Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality JMLR 2024
Wide Two-Layer Networks can Learn from Adversarial Perturbations NIPS 2024
Revisiting Differentially Private ReLU Regression NIPS 2024
Learning via Surrogate PAC-Bayes NIPS 2024
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality NIPS 2024
Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure NIPS 2024
Topological obstruction to the training of shallow ReLU neural networks NIPS 2024
Learnability of Linear Port-Hamiltonian Systems JMLR 2024
Bagging Provides Assumption-free Stability JMLR 2024
Anisotropy is Not Inherent to Transformers NAACL 2024
LeanReasoner: Boosting Complex Logical Reasoning with Lean NAACL 2024
High-dimensional (Group) Adversarial Training in Linear Regression NIPS 2024
Least Squares Regression Can Exhibit Under-Parameterized Double Descent NIPS 2024
Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data NIPS 2024
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing NIPS 2024
Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters NIPS 2024
Test-Time Dynamic Image Fusion NIPS 2024
Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms NIPS 2024
Towards the Dynamics of a DNN Learning Symbolic Interactions NIPS 2024