← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Bounding training data reconstruction in DP-SGD NIPS 2023
ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits AISTATS 2023
Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models EMNLP 2023
Inverse Scaling Can Become U-Shaped EMNLP 2023
Speed-Oblivious Online Scheduling: Knowing (Precise) Speeds is not Necessary ICML 2023
Scaling Laws for BERT in Low-Resource Settings ACL 2023
A Theory of Unsupervised Speech Recognition ACL 2023
Improved Generalization Bound and Learning of Sparsity Patterns for Data-Driven Low-Rank Approximation AISTATS 2023
Testing of Horn Samplers AISTATS 2023
Learning good interventions in causal graphs via covering UAI 2023
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise ICML 2023
Efficiently learning the graph for semi-supervised learning UAI 2023
Active Ranking of Experts Based on their Performances in Many Tasks ICML 2023
Which Invariance Should We Transfer? A Causal Minimax Learning Approach ICML 2023
Delayed Bandits: When Do Intermediate Observations Help? ICML 2023
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making ICML 2023
Atari-5: Distilling the Arcade Learning Environment down to Five Games ICML 2023
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation ICML 2023
Sample Efficiency of Data Augmentation Consistency Regularization AISTATS 2023
The Value of Out-of-Distribution Data ICML 2023
Rethinking Document-Level Relation Extraction: A Reality Check ACL 2023
Benign Overfitting in Two-layer ReLU Convolutional Neural Networks ICML 2023
Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features ICML 2023
Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space ICML 2023
Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data UAI 2023