Learning Theory
6,809 papers
Papers per year
1
16
16
15
17
34
39
36
40
73
85
80
100
126
128
134
186
231
408
512
684
730
905
1,112
883
218
'5
'10
'15
'20
'25
Papers
Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting
AAAI 2025
Online-to-PAC generalization bounds under graph-mixing dependencies
AISTATS 2025
On Memorization of Large Language Models in Logical Reasoning
IJCNLP 2025
On Non-asymptotic Theory of Recurrent Neural Networks in Temporal Point Processes
JMLR 2025
On Speeding Up Language Model Evaluation
ICLR 2025
On Teacher Hacking in Language Model Distillation
ICML 2025
On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory
JMLR 2025
On the Adversarial Robustness of Multi-Kernel Clustering
ICML 2025
On the Benefits of Active Data Collection in Operator Learning
ICML 2025
On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
ICML 2025
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
ICML 2025
On the Convergence of Continuous Single-timescale Actor-critic
ICML 2025
On the Convergence of Projected Policy Gradient for Any Constant Step Sizes
JMLR 2025
On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
ICML 2025
On the Emergence of Position Bias in Transformers
ICML 2025
On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages
AAAI 2025
On the Generalization of Feature Incremental Learning
IJCAI 2025
On the Generalization vs Fidelity Paradox in Knowledge Distillation
ACL 2025
On the Hardness of Bandit Learning
COLT 2025
On the Hardness of Learning One Hidden Layer Neural Networks
ALT 2025
On the Hardness of Training Deep Neural Networks Discretely
AAAI 2025
On the Importance of Embedding Norms in Self-Supervised Learning
ICML 2025
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
ICML 2025
On the Learnability of Distribution Classes with Adaptive Adversaries
ICML 2025
On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
ICLR 2025