← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks NIPS 2023
Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model NIPS 2023
Leveraging the two-timescale regime to demonstrate convergence of neural networks NIPS 2023
What do neural networks learn in image classification? A frequency shortcut perspective ICCV 2023
Leveraging Demonstrations to Improve Online Learning: Quality Matters ICML 2023
Generalization Analysis for Contrastive Representation Learning ICML 2023
PAC Generalization via Invariant Representations ICML 2023
The Power of Uniform Sampling for k-Median ICML 2023
Maximal Initial Learning Rates in Deep ReLU Networks ICML 2023
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources ICML 2023
Differentiable Tree Operations Promote Compositional Generalization ICML 2023
The SSL Interplay: Augmentations, Inductive Bias, and Generalization ICML 2023
On the Role of Attention in Prompt-tuning ICML 2023
Atari-5: Distilling the Arcade Learning Environment down to Five Games ICML 2023
On Single-Index Models beyond Gaussian Data NIPS 2023
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation ICML 2023
Does a Neural Network Really Encode Symbolic Concepts? ICML 2023
Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents ICML 2023
Do Machine Learning Models Learn Statistical Rules Inferred from Data? ICML 2023
Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation ICML 2023
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation ICML 2023
Predictive Flows for Faster Ford-Fulkerson ICML 2023
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks NIPS 2023
Understanding Backdoor Attacks through the Adaptability Hypothesis ICML 2023