Skip to content
conftrace_

Learning Theory

6,809 papers

17
73
128
512
883
'5
'10
'15
'20
'25

Papers

When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards ACL 2024 When Is Inductive Inference Possible? NeurIPS 2024 Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning ICML 2024 Which Is More Effective in Label Noise Cleaning, Correction or Filtering? AAAI 2024 Why are Sensitive Functions Hard for Transformers? ACL 2024 Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning ICML 2024 Why do Variational Autoencoders Really Promote Disentanglement? ICML 2024 Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition ICML 2024 Wide Two-Layer Networks can Learn from Adversarial Perturbations NeurIPS 2024 Winner-takes-all learners are geometry-aware conditional density estimators ICML 2024 Worst-Case Offline Reinforcement Learning with Arbitrary Data Support NeurIPS 2024 XferBench: a Data-Driven Benchmark for Emergent Language NAACL 2024 (ε, u)-Adaptive Regret Minimization in Heavy-Tailed Bandits COLT 2024 H-Consistency Bounds: Characterization and Extensions NeurIPS 2023 H-Consistency Bounds for Pairwise Misranking Loss Surrogates ICML 2023 L_2-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting NeurIPS 2023 $\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks ICLR 2023 A Bayesian Approach To Analysing Training Data Attribution In Deep Learning NeurIPS 2023 A Blackbox Approach to Best of Both Worlds in Bandits and Beyond COLT 2023 A Blessing of Dimensionality in Membership Inference through Regularization AISTATS 2023 Achieving Linear Speedup in Non-IID Federated Bilevel Learning ICML 2023 Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation ICLR 2023 A Competitive Algorithm for Agnostic Active Learning NeurIPS 2023 Active Learning for Single Neuron Models with Lipschitz Non-Linearities AISTATS 2023 Active Ranking of Experts Based on their Performances in Many Tasks ICML 2023