← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Convergence of Actor-Critic with Multi-Layer Neural Networks NIPS 2023
Generalization Bounds using Data-Dependent Fractal Dimensions ICML 2023
Exploring Geometry of Blind Spots in Vision models NIPS 2023
Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex NIPS 2023
On Certified Generalization in Structured Prediction NIPS 2023
Understanding Representation Learnability of Nonlinear Self-Supervised Learning AAAI 2023
On the Sample Complexity of Representation Learning in Multi-Task Bandits with Global and Local Structure AAAI 2023
Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets EMNLP 2023
Approximating Full Conformal Prediction at Scale via Influence Functions AAAI 2023
Theoretical and Practical Perspectives on what Influence Functions Do NIPS 2023
On the Connection between Pre-training Data Diversity and Fine-tuning Robustness NIPS 2023
Which Shortcut Solution Do Question Answering Models Prefer to Learn? AAAI 2023
Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent NIPS 2023
Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets NIPS 2023
On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization AAAI 2023
A Theory of Unsupervised Speech Recognition ACL 2023
Scaling Laws for BERT in Low-Resource Settings ACL 2023
Transformer Working Memory Enables Regular Language Reasoning And Natural Language Length Extrapolation EMNLP 2023
Non-stationary Experimental Design under Linear Trends NIPS 2023
Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness NIPS 2023
Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation COLT 2023
Effects of Human Adversarial and Affable Samples on BERT Generalization EMNLP 2023
Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient COLT 2023
VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation COLT 2023
Exponential Hardness of Reinforcement Learning with Linear Function Approximation COLT 2023